chore(deps): update tools to latest versions (#4370)

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: spiffcs <32073428+spiffcs@users.noreply.github.com>

.binny.yaml

@@ -26,7 +26,7 @@ tools:
   # used for linting
   - name: golangci-lint
     version:
-      want: v2.5.0
+      want: v2.6.2
     method: github-release
     with:
       repo: golangci/golangci-lint
@@ -58,7 +58,7 @@ tools:
   # used to release all artifacts
   - name: goreleaser
     version:
-      want: v2.12.5
+      want: v2.12.7
     method: github-release
     with:
       repo: goreleaser/goreleaser
@@ -90,7 +90,7 @@ tools:
   # used for running all local and CI tasks
   - name: task
     version:
-      want: v3.45.4
+      want: v3.45.5
     method: github-release
     with:
       repo: go-task/task
@@ -98,7 +98,7 @@ tools:
   # used for triggering a release
   - name: gh
     version:
-      want: v2.81.0
+      want: v2.83.1
     method: github-release
     with:
       repo: cli/cli
@@ -114,7 +114,7 @@ tools:
   # used to upload test fixture cache
   - name: yq
     version:
-      want: v4.48.1
+      want: v4.48.2
     method: github-release
     with:
       repo: mikefarah/yq

.github/workflows/codeql-analysis.yml

@@ -47,7 +47,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@f443b600d91635bebf5b0d9ebc620189c0d6fba5 #v3.29.5
+      uses: github/codeql-action/init@014f16e7ab1402f30e7c3329d33797e7948572db #v3.29.5
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -58,7 +58,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@f443b600d91635bebf5b0d9ebc620189c0d6fba5 #v3.29.5
+      uses: github/codeql-action/autobuild@014f16e7ab1402f30e7c3329d33797e7948572db #v3.29.5
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -72,4 +72,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@f443b600d91635bebf5b0d9ebc620189c0d6fba5 #v3.29.5
+      uses: github/codeql-action/analyze@014f16e7ab1402f30e7c3329d33797e7948572db #v3.29.5

.github/workflows/release.yaml

@@ -19,6 +19,16 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - name: Validate Apple notarization credentials
+        run: .tool/quill submission list
+        env:
+          QUILL_NOTARY_ISSUER: ${{ secrets.APPLE_NOTARY_ISSUER }}
+          QUILL_NOTARY_KEY_ID: ${{ secrets.APPLE_NOTARY_KEY_ID }}
+          QUILL_NOTARY_KEY: ${{ secrets.APPLE_NOTARY_KEY }}
+
       - name: Check if running on main
         if: github.ref != 'refs/heads/main'
         # we are using the following flag when running `cosign blob-verify` for checksum signature verification:
@@ -161,7 +171,7 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@f8bdd1d8ac5e901a77a92f111440fdb1b593736b #v0.20.6
+      - uses: anchore/sbom-action@8e94d75ddd33f69f691467e42275782e4bfefe84 #v0.20.9
         continue-on-error: true
         with:
           file: go.mod

.github/workflows/update-anchore-dependencies.yml

@@ -31,11 +31,11 @@ jobs:
         with:
           repos: ${{ github.event.inputs.repos }}
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-bootstrap-tools.yml

@@ -45,11 +45,11 @@ jobs:
             echo "\`\`\`"
           } >> $GITHUB_STEP_SUMMARY
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-cpe-dictionary-index.yml

@@ -14,6 +14,9 @@ env:
 jobs:
   upgrade-cpe-dictionary-index:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
       - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
@@ -22,18 +25,31 @@ jobs:
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        id: bootstrap
 
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
+      - name: Login to GitHub Container Registry
+        run: |
+          echo "${{ secrets.GITHUB_TOKEN }}" | ${{ steps.bootstrap.outputs.oras }} login ghcr.io -u ${{ github.actor }} --password-stdin
 
-      - run: |
-          make generate-cpe-dictionary-index
+      - name: Pull CPE cache from registry
+        run: make generate:cpe-index:cache:pull
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - name: Update CPE cache from NVD API
+        run: make generate:cpe-index:cache:update
+        env:
+          NVD_API_KEY: ${{ secrets.NVD_API_KEY }}
+
+      - name: Generate CPE dictionary index
+        run: make generate:cpe-index:build
+
+      - name: Push updated CPE cache to registry
+        run: make generate:cpe-index:cache:push
+
+      - uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 #v2.1.4
         id: generate-token
         with:
-          app_id: ${{ secrets.TOKEN_APP_ID }}
-          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+          app-id: ${{ secrets.TOKEN_APP_ID }}
+          private-key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
 
       - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
         with:

.github/workflows/update-spdx-license-list.yaml

@@ -0,0 +1,54 @@
+name: PR to update SPDX license list
+on:
+  schedule:
+    - cron: "0 6 * * 1" # every monday at 6 AM UTC
+
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  SLACK_NOTIFICATIONS: true
+
+jobs:
+  upgrade-spdx-license-list:
+    runs-on: ubuntu-latest
+    if: github.repository == 'anchore/syft' # only run for main repo
+    steps:
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+        with:
+          persist-credentials: false
+
+      - name: Bootstrap environment
+        uses: ./.github/actions/bootstrap
+
+      - run: |
+          make generate-license-list
+
+      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+        id: generate-token
+        with:
+          app_id: ${{ secrets.TOKEN_APP_ID }}
+          private_key: ${{ secrets.TOKEN_APP_PRIVATE_KEY }}
+
+      - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e #v7.0.8
+        with:
+          signoff: true
+          delete-branch: true
+          branch: auto/latest-spdx-license-list
+          labels: dependencies
+          commit-message: "chore(deps): update SPDX license list"
+          title: "chore(deps): update SPDX license list"
+          body: |
+            Update SPDX license list based on the latest available list from spdx.org
+          token: ${{ steps.generate-token.outputs.token }}
+
+      - uses: 8398a7/action-slack@77eaa4f1c608a7d68b38af4e3f739dcd8cba273e #v3.19.0
+        with:
+          status: ${{ job.status }}
+          fields: workflow,eventName,job
+          text: Syft SPDX license list update failed
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_TOOLBOX_WEBHOOK_URL }}
+        if: ${{ failure() && env.SLACK_NOTIFICATIONS == 'true' }}

.github/workflows/validations.yaml

@@ -210,7 +210,7 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Install Cosign
-        uses: sigstore/cosign-installer@d7543c93d881b35a8faa02e8e3605f69b7a1ce62 # v3.10.0
+        uses: sigstore/cosign-installer@faadad0cce49287aee09b3a48701e75088a2c6ad # v4.0.0
 
       - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
         with:

.gitignore

@@ -2,6 +2,7 @@
 go.work
 go.work.sum
 .tool-versions
+.python-version
 
 # app configuration
 /.syft.yaml
@@ -72,3 +73,5 @@ cosign.pub
 __pycache__/
 *.py[cod]
 *$py.class
+
+

.goreleaser.yaml

@@ -337,6 +337,7 @@ signs:
     certificate: "${artifact}.pem"
     args:
       - "sign-blob"
+      - "--use-signing-config=false"
       - "--oidc-issuer=https://token.actions.githubusercontent.com"
       - "--output-certificate=${certificate}"
       - "--output-signature=${signature}"

README.md

@@ -106,8 +106,8 @@ syft <image> -o <format>
 Where the `formats` available are:
 - `syft-json`: Use this to get as much information out of Syft as possible!
 - `syft-text`: A row-oriented, human-and-machine-friendly output.
-- `cyclonedx-xml`: A XML report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
-- `cyclonedx-xml@1.5`: A XML report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-xml`: An XML report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
+- `cyclonedx-xml@1.5`: An XML report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
 - `cyclonedx-json`: A JSON report conforming to the [CycloneDX 1.6 specification](https://cyclonedx.org/specification/overview/).
 - `cyclonedx-json@1.5`: A JSON report conforming to the [CycloneDX 1.5 specification](https://cyclonedx.org/specification/overview/).
 - `spdx-tag-value`: A tag-value formatted report conforming to the [SPDX 2.3 specification](https://spdx.github.io/spdx-spec/v2.3/).
@@ -116,7 +116,7 @@ Where the `formats` available are:
 - `spdx-json@2.2`: A JSON report conforming to the [SPDX 2.2 JSON Schema](https://github.com/spdx/spdx-spec/blob/v2.2/schemas/spdx-schema.json).
 - `github-json`: A JSON report conforming to GitHub's dependency snapshot format.
 - `syft-table`: A columnar summary (default).
-- `template`: Lets the user specify the output format. See ["Using templates"](#using-templates) below.
+- `template`: Lets the user specify the output format. See ["Using templates"](https://github.com/anchore/syft/wiki/using-templates) below.
 
 Note that flags using the @<version> can be used for earlier versions of each specification as well.
 
@@ -135,7 +135,7 @@ Note that flags using the @<version> can be used for earlier versions of each sp
 - Go (go.mod, Go binaries)
 - GitHub (workflows, actions)
 - Haskell (cabal, stack)
-- Java (jar, ear, war, par, sar, nar, native-image)
+- Java (jar, ear, war, par, sar, nar, rar, native-image)
 - JavaScript (npm, yarn)
 - Jenkins Plugins (jpi, hpi)
 - Linux kernel archives (vmlinz)

Taskfile.yaml

@@ -1,5 +1,9 @@
 
 version: "3"
+
+includes:
+  generate:cpe-index: ./task.d/generate/cpe-index.yaml
+
 vars:
   OWNER: anchore
   PROJECT: syft
@@ -511,10 +515,11 @@ tasks:
       - "gofmt -s -w ./internal/spdxlicense"
 
   generate-cpe-dictionary-index:
-    desc: Generate the CPE index based off of the latest available CPE dictionary
-    dir: "syft/pkg/cataloger/internal/cpegenerate/dictionary"
+    desc: Generate the CPE index from local cache
     cmds:
-      - "go generate"
+      - task: generate:cpe-index:cache:pull
+      - task: generate:cpe-index:cache:update
+      - task: generate:cpe-index:build
 
 
   ## Build-related targets #################################

cmd/syft/internal/commands/attest.go

@@ -253,7 +253,6 @@ func generateSBOMForAttestation(ctx context.Context, id clio.Identification, opt
 	}
 
 	src, err := getSource(ctx, opts, userInput, stereoscope.RegistryTag)
-
 	if err != nil {
 		return nil, err
 	}

cmd/syft/internal/commands/cataloger_list.go

@@ -87,8 +87,8 @@ func runCatalogerList(opts *catalogerListOptions) error {
 }
 
 func catalogerListReport(opts *catalogerListOptions, allTaskGroups [][]task.Task) (string, error) {
-	defaultCatalogers := options.Flatten(opts.DefaultCatalogers)
-	selectCatalogers := options.Flatten(opts.SelectCatalogers)
+	defaultCatalogers := options.FlattenAndSort(opts.DefaultCatalogers)
+	selectCatalogers := options.FlattenAndSort(opts.SelectCatalogers)
 	selectedTaskGroups, selectionEvidence, err := task.SelectInGroups(
 		allTaskGroups,
 		cataloging.NewSelectionRequest().

cmd/syft/internal/commands/scan.go

@@ -185,7 +185,6 @@ func runScan(ctx context.Context, id clio.Identification, opts *scanOptions, use
 	}
 
 	src, err := getSource(ctx, &opts.Catalog, userInput, sources...)
-
 	if err != nil {
 		return err
 	}

cmd/syft/internal/options/catalog.go

@@ -198,9 +198,10 @@ func (cfg Catalog) ToPackagesConfig() pkgcataloging.Config {
 		},
 		Nix: nix.DefaultConfig().
 			WithCaptureOwnedFiles(cfg.Nix.CaptureOwnedFiles),
-		Python: python.CatalogerConfig{
-			GuessUnpinnedRequirements: cfg.Python.GuessUnpinnedRequirements,
-		},
+		Python: python.DefaultCatalogerConfig().
+			WithSearchRemoteLicenses(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.SearchRemoteLicenses)).
+			WithPypiBaseURL(cfg.Python.PypiBaseURL).
+			WithGuessUnpinnedRequirements(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Python), cfg.Python.GuessUnpinnedRequirements)),
 		JavaArchive: java.DefaultArchiveCatalogerConfig().
 			WithUseMavenLocalRepository(*multiLevelOption(false, enrichmentEnabled(cfg.Enrich, task.Java, task.Maven), cfg.Java.UseMavenLocalRepository)).
 			WithMavenLocalRepositoryDir(cfg.Java.MavenLocalRepositoryDir).
@@ -283,10 +284,10 @@ func (cfg *Catalog) PostLoad() error {
 
 	cfg.From = Flatten(cfg.From)
 
-	cfg.Catalogers = Flatten(cfg.Catalogers)
-	cfg.DefaultCatalogers = Flatten(cfg.DefaultCatalogers)
-	cfg.SelectCatalogers = Flatten(cfg.SelectCatalogers)
-	cfg.Enrich = Flatten(cfg.Enrich)
+	cfg.Catalogers = FlattenAndSort(cfg.Catalogers)
+	cfg.DefaultCatalogers = FlattenAndSort(cfg.DefaultCatalogers)
+	cfg.SelectCatalogers = FlattenAndSort(cfg.SelectCatalogers)
+	cfg.Enrich = FlattenAndSort(cfg.Enrich)
 
 	// for backwards compatibility
 	cfg.DefaultCatalogers = append(cfg.DefaultCatalogers, cfg.Catalogers...)
@@ -311,6 +312,11 @@ func Flatten(commaSeparatedEntries []string) []string {
 			out = append(out, strings.TrimSpace(s))
 		}
 	}
+	return out
+}
+
+func FlattenAndSort(commaSeparatedEntries []string) []string {
+	out := Flatten(commaSeparatedEntries)
 	sort.Strings(out)
 	return out
 }
@@ -320,6 +326,7 @@ var publicisedEnrichmentOptions = []string{
 	task.Golang,
 	task.Java,
 	task.JavaScript,
+	task.Python,
 }
 
 func enrichmentEnabled(enrichDirectives []string, features ...string) *bool {

cmd/syft/internal/options/catalog_test.go

@@ -79,6 +79,98 @@ func TestCatalog_PostLoad(t *testing.T) {
 	}
 }
 
+func TestFlatten(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "preserves order of comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "preserves order across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "trims whitespace",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"registry", "docker", "oci-dir"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "preserves reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"zebra", "yankee", "xray"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Flatten(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+func TestFlattenAndSort(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    []string
+		expected []string
+	}{
+		{
+			name:     "sorts comma-separated values",
+			input:    []string{"registry,docker,oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "sorts across multiple entries",
+			input:    []string{"registry,docker", "oci-dir"},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "trims whitespace and sorts",
+			input:    []string{"  registry  ,  docker  ", "  oci-dir  "},
+			expected: []string{"docker", "oci-dir", "registry"},
+		},
+		{
+			name:     "handles single value",
+			input:    []string{"registry"},
+			expected: []string{"registry"},
+		},
+		{
+			name:     "handles empty input",
+			input:    []string{},
+			expected: nil,
+		},
+		{
+			name:     "sorts reverse alphabetical order",
+			input:    []string{"zebra,yankee,xray"},
+			expected: []string{"xray", "yankee", "zebra"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := FlattenAndSort(tt.input)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
 func Test_enrichmentEnabled(t *testing.T) {
 	tests := []struct {
 		directives string
@@ -139,7 +231,7 @@ func Test_enrichmentEnabled(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(test.directives, func(t *testing.T) {
-			got := enrichmentEnabled(Flatten([]string{test.directives}), test.test)
+			got := enrichmentEnabled(FlattenAndSort([]string{test.directives}), test.test)
 			assert.Equal(t, test.expected, got)
 		})
 	}

cmd/syft/internal/options/python.go

@@ -3,7 +3,9 @@ package options
 import "github.com/anchore/clio"
 
 type pythonConfig struct {
-	GuessUnpinnedRequirements bool `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
+	SearchRemoteLicenses      *bool  `json:"search-remote-licenses" yaml:"search-remote-licenses" mapstructure:"search-remote-licenses"`
+	PypiBaseURL               string `json:"pypi-base-url" yaml:"pypi-base-url" mapstructure:"pypi-base-url"`
+	GuessUnpinnedRequirements *bool  `json:"guess-unpinned-requirements" yaml:"guess-unpinned-requirements" mapstructure:"guess-unpinned-requirements"`
 }
 
 var _ interface {
@@ -11,6 +13,8 @@ var _ interface {
 } = (*pythonConfig)(nil)
 
 func (o *pythonConfig) DescribeFields(descriptions clio.FieldDescriptionSet) {
+	descriptions.Add(&o.SearchRemoteLicenses, `enables Syft to use the network to fill in more detailed license information`)
+	descriptions.Add(&o.PypiBaseURL, `base Pypi url to use`)
 	descriptions.Add(&o.GuessUnpinnedRequirements, `when running across entries in requirements.txt that do not specify a specific version 
 (e.g. "sqlalchemy >= 1.0.0, <= 2.0.0, != 3.0.0, <= 3.0.0"), attempt to guess what the version could
 be based on the version requirements specified (e.g. "1.0.0"). When enabled the lowest expressible version 

cmd/syft/internal/test/integration/catalog_packages_test.go

@@ -25,7 +25,6 @@ func BenchmarkImagePackageCatalogers(b *testing.B) {
 	// get the source object for the image
 	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(b, err)
-
 	b.Cleanup(func() {
 		require.NoError(b, theSource.Close())
 	})
@@ -88,6 +87,7 @@ func TestPkgCoverageImage(t *testing.T) {
 	definedPkgs.Remove(string(pkg.TerraformPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // we have coverage for pear instead
 	definedPkgs.Remove(string(pkg.CondaPkg))
+	definedPkgs.Remove(string(pkg.ModelPkg))
 
 	var cases []testCase
 	cases = append(cases, commonTestCases...)
@@ -162,6 +162,7 @@ func TestPkgCoverageDirectory(t *testing.T) {
 	definedPkgs.Remove(string(pkg.UnknownPkg))
 	definedPkgs.Remove(string(pkg.CondaPkg))
 	definedPkgs.Remove(string(pkg.PhpPeclPkg)) // this is covered as pear packages
+	definedPkgs.Remove(string(pkg.ModelPkg))
 
 	// for directory scans we should not expect to see any of the following package types
 	definedPkgs.Remove(string(pkg.KbPkg))

cmd/syft/internal/test/integration/package_deduplication_test.go

@@ -30,10 +30,10 @@ func TestPackageDeduplication(t *testing.T) {
 			locationCount: map[string]int{
 				"basesystem-11-13.el9":               5, // in all layers
 				"curl-minimal-7.76.1-26.el9_3.2.0.1": 2, // base + wget layer
-				"curl-minimal-7.76.1-31.el9":         3, // curl upgrade layer + all above layers
+				"curl-minimal-7.76.1-31.el9_6.1":     3, // curl upgrade layer + all above layers
 				"wget-1.21.1-8.el9_4":                4, // wget + all above layers
 				"vsftpd-3.0.5-6.el9":                 2, // vsftpd + all above layers
-				"httpd-2.4.62-4.el9":                 1, // last layer
+				"httpd-2.4.62-4.el9_6.4":             1, // last layer
 			},
 		},
 		{
@@ -47,11 +47,11 @@ func TestPackageDeduplication(t *testing.T) {
 				"httpd":        1, // rpm, binary is now excluded by overlap
 			},
 			locationCount: map[string]int{
-				"basesystem-11-13.el9":       1,
-				"curl-minimal-7.76.1-31.el9": 1, // upgrade
-				"wget-1.21.1-8.el9_4":        1,
-				"vsftpd-3.0.5-6.el9":         1,
-				"httpd-2.4.62-4.el9":         1,
+				"basesystem-11-13.el9":           1,
+				"curl-minimal-7.76.1-31.el9_6.1": 1, // upgrade
+				"wget-1.21.1-8.el9_4":            1,
+				"vsftpd-3.0.5-6.el9":             1,
+				"httpd-2.4.62-4.el9_6.4":         1,
 			},
 		},
 	}

cmd/syft/internal/test/integration/test-fixtures/image-vertical-package-dups/Dockerfile

@@ -7,16 +7,16 @@ FROM --platform=linux/amd64 rockylinux:9.3.20231119@sha256:d644d203142cd5b54ad2a
 # copying the RPM DB from each stage to a final stage in separate layers. This will result in a much smaller image.
 
 FROM base AS stage1
-RUN dnf install -y wget
+RUN dnf install -y wget-1.21.1-8.el9_4
 
 FROM stage1 AS stage2
-RUN dnf update -y curl-minimal
+RUN dnf update -y curl-minimal-7.76.1-31.el9_6.1
 
 FROM stage2 AS stage3
-RUN dnf install -y vsftpd
+RUN dnf install -y vsftpd-3.0.5-6.el9
 
 FROM stage3 AS stage4
-RUN dnf install -y httpd
+RUN dnf install -y httpd-2.4.62-4.el9_6.4
 
 FROM scratch
 

cmd/syft/internal/test/integration/utils_test.go

@@ -38,11 +38,11 @@ func catalogFixtureImageWithConfig(t *testing.T, fixtureImageName string, cfg *s
 	// get the source to build an SBOM against
 	theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 	require.NoError(t, err)
-
 	t.Cleanup(func() {
 		require.NoError(t, theSource.Close())
 	})
 
+	// build the SBOM
 	s, err := syft.CreateSBOM(context.Background(), theSource, cfg)
 
 	require.NoError(t, err)
@@ -66,7 +66,7 @@ func catalogDirectory(t *testing.T, dir string, catalogerSelection ...string) (s
 func catalogDirectoryWithConfig(t *testing.T, dir string, cfg *syft.CreateSBOMConfig) (sbom.SBOM, source.Source) {
 	cfg.CatalogerSelection = cfg.CatalogerSelection.WithDefaults(pkgcataloging.DirectoryTag)
 
-	// get the source to build an sbom against
+	// get the source to build an SBOM against
 	theSource, err := syft.GetSource(context.Background(), dir, syft.DefaultGetSourceConfig().WithSources("dir"))
 	require.NoError(t, err)
 	t.Cleanup(func() {

examples/create_custom_sbom/main.go

@@ -23,6 +23,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// will catalog the given source and return a SBOM keeping in mind several configurable options
 	sbom := getSBOM(src)
@@ -46,7 +47,6 @@ func getSource(input string) source.Source {
 	fmt.Println("detecting source type for input:", input, "...")
 
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/create_simple_sbom/main.go

@@ -19,6 +19,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// catalog the given source and return a SBOM
 	sbom := getSBOM(src)
@@ -40,7 +41,6 @@ func imageReference() string {
 
 func getSource(input string) source.Source {
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/select_catalogers/main.go

@@ -19,6 +19,7 @@ const defaultImage = "alpine:3.19"
 func main() {
 	// automagically get a source.Source for arbitrary string input
 	src := getSource(imageReference())
+	defer src.Close()
 
 	// catalog the given source and return a SBOM
 	// let's explicitly use catalogers that are:
@@ -44,7 +45,6 @@ func imageReference() string {
 
 func getSource(input string) source.Source {
 	src, err := syft.GetSource(context.Background(), input, nil)
-
 	if err != nil {
 		panic(err)
 	}

examples/source_from_registry/main.go

@@ -15,6 +15,7 @@ func main() {
 	image := "alpine:3.19"
 
 	src, _ := syft.GetSource(context.Background(), image, syft.DefaultGetSourceConfig().WithSources("registry"))
+	defer src.Close()
 
 	sbom, _ := syft.CreateSBOM(context.Background(), src, syft.DefaultCreateSBOMConfig())
 

go.mod

@@ -11,11 +11,10 @@ require (
 	github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d
 	github.com/acobaugh/osrelease v0.1.0
 	github.com/adrg/xdg v0.5.3
-	github.com/anchore/archiver/v3 v3.5.3-0.20241210171143-5b1d8d1c7c51
 	github.com/anchore/bubbly v0.0.0-20231115134915-def0aba654a9
 	github.com/anchore/clio v0.0.0-20250319180342-2cfe4b0cb716
 	github.com/anchore/fangs v0.0.0-20250319222917-446a1e748ec2
-	github.com/anchore/go-collections v0.0.0-20240216171411-9321230ce537
+	github.com/anchore/go-collections v0.0.0-20251016125210-a3c352120e8c
 	github.com/anchore/go-homedir v0.0.0-20250319154043-c29668562e4d
 	github.com/anchore/go-logger v0.0.0-20250318195838-07ae343dd722
 	github.com/anchore/go-macholibre v0.0.0-20220308212642-53e6d0aaf6fb
@@ -24,7 +23,7 @@ require (
 	github.com/anchore/go-testutils v0.0.0-20200925183923-d5f45b0d3c04
 	github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b
 	github.com/anchore/packageurl-go v0.1.1-0.20250220190351-d62adb6e1115
-	github.com/anchore/stereoscope v0.1.11
+	github.com/anchore/stereoscope v0.1.12
 	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be
 	github.com/aquasecurity/go-pep440-version v0.0.1
 	github.com/bitnami/go-version v0.0.0-20250131085805-b1f57a8634ef
@@ -40,7 +39,7 @@ require (
 	github.com/dustin/go-humanize v1.0.1
 	github.com/elliotchance/phpserialize v1.4.0
 	github.com/facebookincubator/nvdtools v0.1.5
-	github.com/github/go-spdx/v2 v2.3.3
+	github.com/github/go-spdx/v2 v2.3.4
 	github.com/gkampitakis/go-snaps v0.5.15
 	github.com/go-git/go-billy/v5 v5.6.2
 	github.com/go-git/go-git/v5 v5.16.3
@@ -53,19 +52,19 @@ require (
 	github.com/google/uuid v1.6.0
 	github.com/gookit/color v1.6.0
 	github.com/hashicorp/go-cleanhttp v0.5.2
-	github.com/hashicorp/go-getter v1.8.2
+	github.com/hashicorp/go-getter v1.8.3
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/hashicorp/hcl/v2 v2.24.0
 	github.com/iancoleman/strcase v0.3.0
 	github.com/invopop/jsonschema v0.7.0
-	github.com/jedib0t/go-pretty/v6 v6.6.8
+	github.com/jedib0t/go-pretty/v6 v6.7.1
 	github.com/jinzhu/copier v0.4.0
 	github.com/kastenhq/goversion v0.0.0-20230811215019-93b2f8823953
 	github.com/magiconair/properties v1.8.10
 	github.com/mholt/archives v0.1.5
 	github.com/moby/sys/mountinfo v0.7.2
 	github.com/nix-community/go-nix v0.0.0-20250101154619-4bdde671e0a1
-	github.com/olekukonko/tablewriter v1.0.9
+	github.com/olekukonko/tablewriter v1.1.1
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/pelletier/go-toml v1.9.5
 	github.com/quasilyte/go-ruleguard/dsl v0.3.23
@@ -90,9 +89,9 @@ require (
 	go.uber.org/goleak v1.3.0
 	go.yaml.in/yaml/v3 v3.0.4
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b
-	golang.org/x/mod v0.29.0
+	golang.org/x/mod v0.30.0
 	golang.org/x/net v0.46.0
-	modernc.org/sqlite v1.39.1
+	modernc.org/sqlite v1.40.0
 )
 
 require (
@@ -131,7 +130,7 @@ require (
 	github.com/charmbracelet/x/term v0.2.1 // indirect
 	github.com/cloudflare/circl v1.6.1 // indirect
 	github.com/containerd/cgroups v1.1.0 // indirect
-	github.com/containerd/containerd v1.7.28 // indirect
+	github.com/containerd/containerd v1.7.29 // indirect
 	github.com/containerd/containerd/api v1.8.0 // indirect
 	github.com/containerd/continuity v0.4.4 // indirect
 	github.com/containerd/errdefs v1.0.0 // indirect
@@ -142,7 +141,7 @@ require (
 	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
 	github.com/containerd/ttrpc v1.2.7 // indirect
 	github.com/containerd/typeurl/v2 v2.2.0 // indirect
-	github.com/cyphar/filepath-securejoin v0.4.1 // indirect
+	github.com/cyphar/filepath-securejoin v0.6.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/docker/cli v28.5.1+incompatible // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
@@ -168,7 +167,6 @@ require (
 	github.com/goccy/go-yaml v1.18.0
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20241129210726-2c02b8208cf8 // indirect
-	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e // indirect
 	github.com/google/s2a-go v0.1.8 // indirect
 	github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect
@@ -191,7 +189,7 @@ require (
 	github.com/mattn/go-colorable v0.1.14 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75 // indirect
-	github.com/mattn/go-runewidth v0.0.16 // indirect
+	github.com/mattn/go-runewidth v0.0.19 // indirect
 	github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d // indirect
 	github.com/mikelolasagasti/xz v1.0.1 // indirect
 	github.com/minio/minlz v1.0.1 // indirect
@@ -209,13 +207,9 @@ require (
 	github.com/muesli/cancelreader v0.2.2 // indirect
 	github.com/muesli/termenv v0.16.0 // indirect
 	github.com/ncruces/go-strftime v0.1.9 // indirect
-	github.com/nwaples/rardecode v1.1.3 // indirect
-	github.com/nwaples/rardecode/v2 v2.2.0 // indirect
-	github.com/olekukonko/errors v1.1.0 // indirect
-	github.com/olekukonko/ll v0.0.9 // indirect
 	github.com/opencontainers/image-spec v1.1.1 // indirect
 	github.com/opencontainers/runtime-spec v1.1.0 // indirect
-	github.com/opencontainers/selinux v1.11.0 // indirect
+	github.com/opencontainers/selinux v1.13.0 // indirect
 	github.com/pborman/indent v1.2.1 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.3 // indirect
 	github.com/pierrec/lz4/v4 v4.1.22 // indirect
@@ -270,7 +264,7 @@ require (
 	golang.org/x/sys v0.37.0 // indirect
 	golang.org/x/term v0.36.0 // indirect
 	golang.org/x/text v0.30.0 // indirect
-	golang.org/x/time v0.12.0 // indirect
+	golang.org/x/time v0.14.0
 	golang.org/x/tools v0.38.0
 	golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 // indirect
 	google.golang.org/api v0.203.0 // indirect
@@ -287,6 +281,12 @@ require (
 )
 
 require (
+	github.com/cespare/xxhash/v2 v2.3.0
+	github.com/gpustack/gguf-parser-go v0.22.1
+)
+
+require (
+	cyphar.com/go-pathrs v0.2.1 // indirect
 	github.com/aws/aws-sdk-go-v2 v1.36.5 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.10 // indirect
 	github.com/aws/aws-sdk-go-v2/config v1.29.17 // indirect
@@ -305,7 +305,20 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.30.3 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sts v1.34.0 // indirect
 	github.com/aws/smithy-go v1.22.4 // indirect
+	github.com/clipperhouse/displaywidth v0.3.1 // indirect
+	github.com/clipperhouse/stringish v0.1.1 // indirect
+	github.com/clipperhouse/uax29/v2 v2.2.0 // indirect
 	github.com/hashicorp/aws-sdk-go-base/v2 v2.0.0-beta.65 // indirect
+	github.com/henvic/httpretty v0.1.4 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/nwaples/rardecode/v2 v2.2.0 // indirect
+	github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6 // indirect
+	github.com/olekukonko/errors v1.1.0 // indirect
+	github.com/olekukonko/ll v0.1.2 // indirect
+	github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d // indirect
+	gonum.org/v1/gonum v0.15.1 // indirect
 )
 
 retract (

go.sum

@@ -59,6 +59,8 @@ cloud.google.com/go/storage v1.8.0/go.mod h1:Wv1Oy7z6Yz3DshWRJFhqM/UCfaWIRTdp0RX
 cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9ullr3+Kg0=
 cloud.google.com/go/storage v1.43.0 h1:CcxnSohZwizt4LCzQHWvBf1/kvtHUn7gk9QERXPyXFs=
 cloud.google.com/go/storage v1.43.0/go.mod h1:ajvxEa7WmZS1PxvKRq4bq0tFT3vMd502JwstCcYv0Q0=
+cyphar.com/go-pathrs v0.2.1 h1:9nx1vOgwVvX1mNBWDu93+vaceedpbsDqo+XuBGL40b8=
+cyphar.com/go-pathrs v0.2.1/go.mod h1:y8f1EMG7r+hCuFf/rXsKqMJrJAUoADZGNh5/vZPKcGc=
 dario.cat/mergo v1.0.1 h1:Ra4+bf83h2ztPIQYNP99R6m+Y7KfnARDfID+a+vLl4s=
 dario.cat/mergo v1.0.1/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk=
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
@@ -108,16 +110,14 @@ github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuy
 github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
-github.com/anchore/archiver/v3 v3.5.3-0.20241210171143-5b1d8d1c7c51 h1:yhk+P8lF3ZiROjmaVRao9WGTRo4b/wYjoKEiAHWrKwc=
-github.com/anchore/archiver/v3 v3.5.3-0.20241210171143-5b1d8d1c7c51/go.mod h1:nwuGSd7aZp0rtYt79YggCGafz1RYsclE7pi3fhLwvuw=
 github.com/anchore/bubbly v0.0.0-20231115134915-def0aba654a9 h1:p0ZIe0htYOX284Y4axJaGBvXHU0VCCzLN5Wf5XbKStU=
 github.com/anchore/bubbly v0.0.0-20231115134915-def0aba654a9/go.mod h1:3ZsFB9tzW3vl4gEiUeuSOMDnwroWxIxJelOOHUp8dSw=
 github.com/anchore/clio v0.0.0-20250319180342-2cfe4b0cb716 h1:2sIdYJlQESEnyk3Y0WD2vXWW5eD2iMz9Ev8fj1Z8LNA=
 github.com/anchore/clio v0.0.0-20250319180342-2cfe4b0cb716/go.mod h1:Utb9i4kwiCWvqAIxZaJeMIXFO9uOgQXlvH2BfbfO/zI=
 github.com/anchore/fangs v0.0.0-20250319222917-446a1e748ec2 h1:GC2QaO0YsmjpsZ4rtVKv9DnproIxqqn+qkskpc+i8MA=
 github.com/anchore/fangs v0.0.0-20250319222917-446a1e748ec2/go.mod h1:XUbUECwVKuD3qYRUj+QZIOHjyyXua2gFmVjKA40iHXA=
-github.com/anchore/go-collections v0.0.0-20240216171411-9321230ce537 h1:GjNGuwK5jWjJMyVppBjYS54eOiiSNv4Ba869k4wh72Q=
-github.com/anchore/go-collections v0.0.0-20240216171411-9321230ce537/go.mod h1:1aiktV46ATCkuVg0O573ZrH56BUawTECPETbZyBcqT8=
+github.com/anchore/go-collections v0.0.0-20251016125210-a3c352120e8c h1:eoJXyC0n7DZ4YvySG/ETdYkTar2Due7eH+UmLK6FbrA=
+github.com/anchore/go-collections v0.0.0-20251016125210-a3c352120e8c/go.mod h1:1aiktV46ATCkuVg0O573ZrH56BUawTECPETbZyBcqT8=
 github.com/anchore/go-homedir v0.0.0-20250319154043-c29668562e4d h1:gT69osH9AsdpOfqxbRwtxcNnSZ1zg4aKy2BevO3ZBdc=
 github.com/anchore/go-homedir v0.0.0-20250319154043-c29668562e4d/go.mod h1:PhSnuFYknwPZkOWKB1jXBNToChBA+l0FjwOxtViIc50=
 github.com/anchore/go-logger v0.0.0-20250318195838-07ae343dd722 h1:2SqmFgE7h+Ql4VyBzhjLkRF/3gDrcpUBj8LjvvO6OOM=
@@ -138,8 +138,8 @@ github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b h1:e1bmaoJfZV
 github.com/anchore/go-version v1.2.2-0.20200701162849-18adb9c92b9b/go.mod h1:Bkc+JYWjMCF8OyZ340IMSIi2Ebf3uwByOk6ho4wne1E=
 github.com/anchore/packageurl-go v0.1.1-0.20250220190351-d62adb6e1115 h1:ZyRCmiEjnoGJZ1+Ah0ZZ/mKKqNhGcUZBl0s7PTTDzvY=
 github.com/anchore/packageurl-go v0.1.1-0.20250220190351-d62adb6e1115/go.mod h1:KoYIv7tdP5+CC9VGkeZV4/vGCKsY55VvoG+5dadg4YI=
-github.com/anchore/stereoscope v0.1.11 h1:YP/XUNcJyMbOOPAWPkeZNCVlKKTRO2cnBTEeUW6I40Y=
-github.com/anchore/stereoscope v0.1.11/go.mod h1:G3PZlzPbxFhylj9pQwtqfVPaahuWmy/UCtv5FTIIMvg=
+github.com/anchore/stereoscope v0.1.12 h1:4T/10G7Nb98UoJBKVvAIhsAtrR63lZXxMJb/Qfw5inw=
+github.com/anchore/stereoscope v0.1.12/go.mod h1:G3PZlzPbxFhylj9pQwtqfVPaahuWmy/UCtv5FTIIMvg=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
 github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
@@ -227,7 +227,6 @@ github.com/cenkalti/backoff/v4 v4.2.1 h1:y4OZtCnogmCPw98Zjyt5a6+QwPLGkiQsYW5oUqy
 github.com/cenkalti/backoff/v4 v4.2.1/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/census-instrumentation/opencensus-proto v0.3.0/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
-github.com/cespare/xxhash v1.1.0 h1:a6HrQnmkObjyL+Gs60czilIUGqrzKutQD6XZog3p+ko=
 github.com/cespare/xxhash v1.1.0/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
 github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -263,6 +262,12 @@ github.com/chzyer/test v1.0.0/go.mod h1:2JlltgoNkt4TW/z9V/IzDdFaMTM2JPIi26O1pF38
 github.com/circonus-labs/circonus-gometrics v2.3.1+incompatible/go.mod h1:nmEj6Dob7S7YxXgwXpfOuvO54S+tGdZdw9fuRZt25Ag=
 github.com/circonus-labs/circonusllhist v0.1.3/go.mod h1:kMXHVDlOchFAehlya5ePtbp5jckzBHf4XRpQvBOLI+I=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
+github.com/clipperhouse/displaywidth v0.3.1 h1:k07iN9gD32177o1y4O1jQMzbLdCrsGJh+blirVYybsk=
+github.com/clipperhouse/displaywidth v0.3.1/go.mod h1:tgLJKKyaDOCadywag3agw4snxS5kYEuYR6Y9+qWDDYM=
+github.com/clipperhouse/stringish v0.1.1 h1:+NSqMOr3GR6k1FdRhhnXrLfztGzuG+VuFDfatpWHKCs=
+github.com/clipperhouse/stringish v0.1.1/go.mod h1:v/WhFtE1q0ovMta2+m+UbpZ+2/HEXNWYXQgCt4hdOzA=
+github.com/clipperhouse/uax29/v2 v2.2.0 h1:ChwIKnQN3kcZteTXMgb1wztSgaU+ZemkgWdohwgs8tY=
+github.com/clipperhouse/uax29/v2 v2.2.0/go.mod h1:EFJ2TJMRUaplDxHKj1qAEhCtQPW2tJSwu5BF98AuoVM=
 github.com/cloudflare/circl v1.6.1 h1:zqIqSPIndyBh1bjLVVDHMPpVKqp8Su/V+6MeDzzQBQ0=
 github.com/cloudflare/circl v1.6.1/go.mod h1:uddAzsPgqdMAYatqJ0lsjX1oECcQLIlRpzZh3pJrofs=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
@@ -277,8 +282,8 @@ github.com/cncf/xds/go v0.0.0-20211011173535-cb28da3451f1/go.mod h1:eXthEFrGJvWH
 github.com/cncf/xds/go v0.0.0-20211130200136-a8f946100490/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
 github.com/containerd/cgroups v1.1.0 h1:v8rEWFl6EoqHB+swVNjVoCJE8o3jX7e8nqBGPLaDFBM=
 github.com/containerd/cgroups v1.1.0/go.mod h1:6ppBcbh/NOOUU+dMKrykgaBnK9lCIBxHqJDGwsa1mIw=
-github.com/containerd/containerd v1.7.28 h1:Nsgm1AtcmEh4AHAJ4gGlNSaKgXiNccU270Dnf81FQ3c=
-github.com/containerd/containerd v1.7.28/go.mod h1:azUkWcOvHrWvaiUjSQH0fjzuHIwSPg1WL5PshGP4Szs=
+github.com/containerd/containerd v1.7.29 h1:90fWABQsaN9mJhGkoVnuzEY+o1XDPbg9BTC9QTAHnuE=
+github.com/containerd/containerd v1.7.29/go.mod h1:azUkWcOvHrWvaiUjSQH0fjzuHIwSPg1WL5PshGP4Szs=
 github.com/containerd/containerd/api v1.8.0 h1:hVTNJKR8fMc/2Tiw60ZRijntNMd1U+JVMyTRdsD2bS0=
 github.com/containerd/containerd/api v1.8.0/go.mod h1:dFv4lt6S20wTu/hMcP4350RL87qPWLVa/OHOwmmdnYc=
 github.com/containerd/continuity v0.4.4 h1:/fNVfTJ7wIl/YPMHjf+5H32uFhl63JucB34PlCpMKII=
@@ -304,8 +309,8 @@ github.com/coreos/go-systemd/v22 v22.3.2/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSV
 github.com/cpuguy83/go-md2man/v2 v2.0.1/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
-github.com/cyphar/filepath-securejoin v0.4.1 h1:JyxxyPEaktOD+GAnqIqTf9A8tHyAG22rowi7HkoSU1s=
-github.com/cyphar/filepath-securejoin v0.4.1/go.mod h1:Sdj7gXlvMcPZsbhwhQ33GguGLDGQL7h7bg04C/+u9jI=
+github.com/cyphar/filepath-securejoin v0.6.0 h1:BtGB77njd6SVO6VztOHfPxKitJvd/VPT+OFBFMOi1Is=
+github.com/cyphar/filepath-securejoin v0.6.0/go.mod h1:A8hd4EnAeyujCJRrICiOWqjS1AX0a9kM5XL+NwKoYSc=
 github.com/dave/jennifer v1.7.1 h1:B4jJJDHelWcDhlRQxWeo0Npa/pYKBLrirAQoTN45txo=
 github.com/dave/jennifer v1.7.1/go.mod h1:nXbxhEmQfOZhWml3D1cDK5M1FLnMSozpbFN/m3RmGZc=
 github.com/davecgh/go-spew v0.0.0-20161028175848-04cdfd42973b/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -385,8 +390,8 @@ github.com/fsnotify/fsnotify v1.8.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8
 github.com/gabriel-vasile/mimetype v1.4.9 h1:5k+WDwEsD9eTLL8Tz3L0VnmVh9QxGjRmjBvAG7U/oYY=
 github.com/gabriel-vasile/mimetype v1.4.9/go.mod h1:WnSQhFKJuBlRyLiKohA/2DtIlPFAbguNaG7QCHcyGok=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
-github.com/github/go-spdx/v2 v2.3.3 h1:QI7evnHWEfWkT54eJwkoV/f3a0xD3gLlnVmT5wQG6LE=
-github.com/github/go-spdx/v2 v2.3.3/go.mod h1:2ZxKsOhvBp+OYBDlsGnUMcchLeo2mrpEBn2L1C+U3IQ=
+github.com/github/go-spdx/v2 v2.3.4 h1:6VNAsYWvQge+SOeoubTlH81MY21d5uekXNIRGfXMNXo=
+github.com/github/go-spdx/v2 v2.3.4/go.mod h1:7LYNCshU2Gj17qZ0heJ5CQUKWWmpd98K7o93K8fJSMk=
 github.com/gkampitakis/ciinfo v0.3.2 h1:JcuOPk8ZU7nZQjdUhctuhQofk7BGHuIy0c9Ez8BNhXs=
 github.com/gkampitakis/ciinfo v0.3.2/go.mod h1:1NIwaOcFChN4fa/B0hEBdAb6npDlFL8Bwx4dfRLRqAo=
 github.com/gkampitakis/go-diff v1.3.2 h1:Qyn0J9XJSDTgnsgHRdz9Zp24RaJeKMUHg2+PDZZdC4M=
@@ -472,8 +477,6 @@ github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiu
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
 github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
 github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
-github.com/golang/snappy v0.0.4 h1:yAGX7huGHXlcLOEtBnF4w7FQwA26wojNCwOYAEhLjQM=
-github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
 github.com/google/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
@@ -541,6 +544,8 @@ github.com/gookit/assert v0.1.1/go.mod h1:jS5bmIVQZTIwk42uXl4lyj4iaaxx32tqH16CFj
 github.com/gookit/color v1.2.5/go.mod h1:AhIE+pS6D4Ql0SQWbBeXPHw7gY0/sjHoA4s/n1KB7xg=
 github.com/gookit/color v1.6.0 h1:JjJXBTk1ETNyqyilJhkTXJYYigHG24TM9Xa2M1xAhRA=
 github.com/gookit/color v1.6.0/go.mod h1:9ACFc7/1IpHGBW8RwuDm/0YEnhg3dwwXpoMsmtyHfjs=
+github.com/gpustack/gguf-parser-go v0.22.1 h1:FRnEDWqT0Rcplr/R9ctCRSN2+3DhVsf6dnR5/i9JA4E=
+github.com/gpustack/gguf-parser-go v0.22.1/go.mod h1:y4TwTtDqFWTK+xvprOjRUh+dowgU2TKCX37vRKvGiZ0=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
 github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.16.0 h1:YBftPWNWd4WwGqtY2yeZL2ef8rHAxPBD8KFhJpmcqms=
@@ -556,8 +561,8 @@ github.com/hashicorp/go-cleanhttp v0.5.0/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtng
 github.com/hashicorp/go-cleanhttp v0.5.1/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtngrth3wmdIIUrZ80=
 github.com/hashicorp/go-cleanhttp v0.5.2 h1:035FKYIWjmULyFRBKPs8TBQoi0x6d9G4xc9neXJWAZQ=
 github.com/hashicorp/go-cleanhttp v0.5.2/go.mod h1:kO/YDlP8L1346E6Sodw+PrpBSV4/SoxCXGY6BqNFT48=
-github.com/hashicorp/go-getter v1.8.2 h1:CGCK+bZQLl44PYiwJweVzfpjg7bBwtuXu3AGcLiod2o=
-github.com/hashicorp/go-getter v1.8.2/go.mod h1:CUTt9x2bCtJ/sV8ihgrITL3IUE+0BE1j/e4n5P/GIM4=
+github.com/hashicorp/go-getter v1.8.3 h1:gIS+oTNv3kyYAvlUVgMR46MiG0bM0KuSON/KZEvRoRg=
+github.com/hashicorp/go-getter v1.8.3/go.mod h1:CUTt9x2bCtJ/sV8ihgrITL3IUE+0BE1j/e4n5P/GIM4=
 github.com/hashicorp/go-hclog v0.12.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
 github.com/hashicorp/go-hclog v1.0.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
 github.com/hashicorp/go-immutable-radix v1.0.0/go.mod h1:0y9vanUI8NX6FsYoO3zeMjhV/C5i9g4Q3DwcSNZ4P60=
@@ -590,6 +595,8 @@ github.com/hashicorp/memberlist v0.2.2/go.mod h1:MS2lj3INKhZjWNqd3N0m3J+Jxf3DAOn
 github.com/hashicorp/memberlist v0.3.0/go.mod h1:MS2lj3INKhZjWNqd3N0m3J+Jxf3DAOnAH9VT3Sh9MUE=
 github.com/hashicorp/serf v0.9.5/go.mod h1:UWDWwZeL5cuWDJdl0C6wrvrUwEqtQ4ZKBKKENpqIUyk=
 github.com/hashicorp/serf v0.9.6/go.mod h1:TXZNMjZQijwlDvp+r0b63xZ45H7JmCmgg4gpTwn9UV4=
+github.com/henvic/httpretty v0.1.4 h1:Jo7uwIRWVFxkqOnErcoYfH90o3ddQyVrSANeS4cxYmU=
+github.com/henvic/httpretty v0.1.4/go.mod h1:Dn60sQTZfbt2dYsdUSNsCljyF4AfdqnuJFDLJA1I4AM=
 github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI=
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
 github.com/iancoleman/orderedmap v0.0.0-20190318233801-ac98e3ecb4b0/go.mod h1:N0Wam8K1arqPXNWjMo21EXnBPOPp36vB07FNRdD2geA=
@@ -609,14 +616,15 @@ github.com/invopop/jsonschema v0.7.0 h1:2vgQcBz1n256N+FpX3Jq7Y17AjYt46Ig3zIWyy77
 github.com/invopop/jsonschema v0.7.0/go.mod h1:O9uiLokuu0+MGFlyiaqtWxwqJm41/+8Nj0lD7A36YH0=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 h1:BQSFePA1RWJOlocH6Fxy8MmwDt+yVQYULKfN0RoTN8A=
 github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99/go.mod h1:1lJo3i6rXxKeerYnT8Nvf0QmHCRC1n8sfWVwXF2Frvo=
-github.com/jedib0t/go-pretty/v6 v6.6.8 h1:JnnzQeRz2bACBobIaa/r+nqjvws4yEhcmaZ4n1QzsEc=
-github.com/jedib0t/go-pretty/v6 v6.6.8/go.mod h1:YwC5CE4fJ1HFUDeivSV1r//AmANFHyqczZk+U6BDALU=
+github.com/jedib0t/go-pretty/v6 v6.7.1 h1:bHDSsj93NuJ563hHuM7ohk/wpX7BmRFNIsVv1ssI2/M=
+github.com/jedib0t/go-pretty/v6 v6.7.1/go.mod h1:YwC5CE4fJ1HFUDeivSV1r//AmANFHyqczZk+U6BDALU=
 github.com/jinzhu/copier v0.4.0 h1:w3ciUoD19shMCRargcpm0cm91ytaBhDvuRpz1ODO/U8=
 github.com/jinzhu/copier v0.4.0/go.mod h1:DfbEm0FYsaqBcKcFuvmOZb218JkPGtvSHsKg8S8hyyg=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.11/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
 github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
@@ -676,8 +684,8 @@ github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWE
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75 h1:P8UmIzZMYDR+NGImiFvErt6VWfIRPuGM+vyjiEdkmIw=
 github.com/mattn/go-localereader v0.0.2-0.20220822084749-2491eb6c1c75/go.mod h1:8fBrzywKY7BI3czFoHkuzRoWE9C+EiG4R1k4Cjx5p88=
-github.com/mattn/go-runewidth v0.0.16 h1:E5ScNMtiwvlvB5paMFdw9p4kSQzbXFikJ5SQO6TULQc=
-github.com/mattn/go-runewidth v0.0.16/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
+github.com/mattn/go-runewidth v0.0.19 h1:v++JhqYnZuu5jSKrk9RbgF5v4CGUjqRfBm05byFGLdw=
+github.com/mattn/go-runewidth v0.0.19/go.mod h1:XBkDxAl56ILZc9knddidhrOlY5R/pDhgLpndooCuJAs=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
 github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d h1:5PJl274Y63IEHC+7izoQE9x6ikvDFZS2mDVS3drnohI=
 github.com/mgutz/ansi v0.0.0-20200706080929-d51e80ef957d/go.mod h1:01TrycV0kFyexm33Z7vhZRXopbI8J3TDReVlkTgMUxE=
@@ -722,9 +730,11 @@ github.com/moby/sys/userns v0.1.0/go.mod h1:IHUYgu/kao6N8YZlp9Cf444ySSvCmDlmzUcY
 github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA=
 github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
 github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
@@ -741,16 +751,16 @@ github.com/nix-community/go-nix v0.0.0-20250101154619-4bdde671e0a1 h1:kpt9ZfKcm+
 github.com/nix-community/go-nix v0.0.0-20250101154619-4bdde671e0a1/go.mod h1:qgCw4bBKZX8qMgGeEZzGFVT3notl42dBjNqO2jut0M0=
 github.com/nsf/jsondiff v0.0.0-20210926074059-1e845ec5d249 h1:NHrXEjTNQY7P0Zfx1aMrNhpgxHmow66XQtm0aQLY0AE=
 github.com/nsf/jsondiff v0.0.0-20210926074059-1e845ec5d249/go.mod h1:mpRZBD8SJ55OIICQ3iWH0Yz3cjzA61JdqMLoWXeB2+8=
-github.com/nwaples/rardecode v1.1.3 h1:cWCaZwfM5H7nAD6PyEdcVnczzV8i/JtotnyW/dD9lEc=
-github.com/nwaples/rardecode v1.1.3/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
 github.com/nwaples/rardecode/v2 v2.2.0 h1:4ufPGHiNe1rYJxYfehALLjup4Ls3ck42CWwjKiOqu0A=
 github.com/nwaples/rardecode/v2 v2.2.0/go.mod h1:7uz379lSxPe6j9nvzxUZ+n7mnJNgjsRNb6IbvGVHRmw=
+github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6 h1:zrbMGy9YXpIeTnGj4EljqMiZsIcE09mmF8XsD5AYOJc=
+github.com/olekukonko/cat v0.0.0-20250911104152-50322a0618f6/go.mod h1:rEKTHC9roVVicUIfZK7DYrdIoM0EOr8mK1Hj5s3JjH0=
 github.com/olekukonko/errors v1.1.0 h1:RNuGIh15QdDenh+hNvKrJkmxxjV4hcS50Db478Ou5sM=
 github.com/olekukonko/errors v1.1.0/go.mod h1:ppzxA5jBKcO1vIpCXQ9ZqgDh8iwODz6OXIGKU8r5m4Y=
-github.com/olekukonko/ll v0.0.9 h1:Y+1YqDfVkqMWuEQMclsF9HUR5+a82+dxJuL1HHSRpxI=
-github.com/olekukonko/ll v0.0.9/go.mod h1:En+sEW0JNETl26+K8eZ6/W4UQ7CYSrrgg/EdIYT2H8g=
-github.com/olekukonko/tablewriter v1.0.9 h1:XGwRsYLC2bY7bNd93Dk51bcPZksWZmLYuaTHR0FqfL8=
-github.com/olekukonko/tablewriter v1.0.9/go.mod h1:5c+EBPeSqvXnLLgkm9isDdzR3wjfBkHR9Nhfp3NWrzo=
+github.com/olekukonko/ll v0.1.2 h1:lkg/k/9mlsy0SxO5aC+WEpbdT5K83ddnNhAepz7TQc0=
+github.com/olekukonko/ll v0.1.2/go.mod h1:b52bVQRRPObe+yyBl0TxNfhesL0nedD4Cht0/zx55Ew=
+github.com/olekukonko/tablewriter v1.1.1 h1:b3reP6GCfrHwmKkYwNRFh2rxidGHcT6cgxj/sHiDDx0=
+github.com/olekukonko/tablewriter v1.1.1/go.mod h1:De/bIcTF+gpBDB3Alv3fEsZA+9unTsSzAg/ZGADCtn4=
 github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
 github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
@@ -759,8 +769,8 @@ github.com/opencontainers/image-spec v1.1.1 h1:y0fUlFfIZhPF1W537XOLg0/fcx6zcHCJw
 github.com/opencontainers/image-spec v1.1.1/go.mod h1:qpqAh3Dmcf36wStyyWU+kCeDgrGnAve2nCC8+7h8Q0M=
 github.com/opencontainers/runtime-spec v1.1.0 h1:HHUyrt9mwHUjtasSbXSMvs4cyFxh+Bll4AjJ9odEGpg=
 github.com/opencontainers/runtime-spec v1.1.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU=
-github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
+github.com/opencontainers/selinux v1.13.0 h1:Zza88GWezyT7RLql12URvoxsbLfjFx988+LGaWfbL84=
+github.com/opencontainers/selinux v1.13.0/go.mod h1:XxWTed+A/s5NNq4GmYScVy+9jzXhGBVEOAyucdRUY8s=
 github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0=
 github.com/pascaldekloe/goe v0.0.0-20180627143212-57f6aae5913c/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
 github.com/pascaldekloe/goe v0.1.0/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
@@ -809,7 +819,6 @@ github.com/quasilyte/go-ruleguard/dsl v0.3.23 h1:lxjt5B6ZCiBeeNO8/oQsegE6fLeCzuM
 github.com/quasilyte/go-ruleguard/dsl v0.3.23/go.mod h1:KeCP03KrjuSO0H1kTuZQCWlQPulDV6YMIXmpQss17rU=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
-github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
 github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
@@ -851,6 +860,8 @@ github.com/sirupsen/logrus v1.9.4-0.20230606125235-dd1b4c2e81af h1:Sp5TG9f7K39yf
 github.com/sirupsen/logrus v1.9.4-0.20230606125235-dd1b4c2e81af/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/skeema/knownhosts v1.3.1 h1:X2osQ+RAjK76shCbvhHHHVl3ZlgDm8apHEHFqRjnBY8=
 github.com/skeema/knownhosts v1.3.1/go.mod h1:r7KTdC8l4uxWRyK2TpQZ/1o5HaSzh06ePQNxPwTcfiY=
+github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d h1:3VwvTjiRPA7cqtgOWddEL+JrcijMlXUmj99c/6YyZoY=
+github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d/go.mod h1:tAG61zBM1DYRaGIPloumExGvScf08oHuo0kFoOqdbT0=
 github.com/sorairolake/lzip-go v0.3.8 h1:j5Q2313INdTA80ureWYRhX+1K78mUXfMoPZCw/ivWik=
 github.com/sorairolake/lzip-go v0.3.8/go.mod h1:JcBqGMV0frlxwrsE9sMWXDjqn3EeVf0/54YPsw66qkU=
 github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
@@ -1061,8 +1072,8 @@ golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.5.0/go.mod h1:5OXOZSfqPIIbmVBIIKWRFfZjPR0E5r58TLhUjH0a2Ro=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA=
-golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w=
+golang.org/x/mod v0.30.0 h1:fDEXFVZ/fmCKProc/yAXXUijritrDzahmwwefnjoPFk=
+golang.org/x/mod v0.30.0/go.mod h1:lAsf5O2EvJeSFMiBxXDki7sCgAxEUcZHXoXMKT4GJKc=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181023162649-9b4f9f5ad519/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -1239,8 +1250,8 @@ golang.org/x/text v0.30.0/go.mod h1:yDdHFIX9t+tORqspjENWgzaCVXgk0yYnYuSZ8UzzBVM=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
-golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
+golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
+golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -1304,6 +1315,8 @@ golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 h1:+cNy6SZtPcJQH3LJVLOSmiC7MMxXNOb3PU/VUEz+EhU=
 golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028/go.mod h1:NDW/Ps6MPRej6fsCIbMTohpP40sJ/P/vI1MoTEGwX90=
+gonum.org/v1/gonum v0.15.1 h1:FNy7N6OUZVUaWG9pTiD+jlhdQ3lMP+/LcTpJ6+a8sQ0=
+gonum.org/v1/gonum v0.15.1/go.mod h1:eZTZuRFrzu5pcyjN5wJhcIhnUdNijYxX1T2IcrOGY0o=
 google.golang.org/api v0.4.0/go.mod h1:8k5glujaEP+g9n7WNsDg8QP6cUVNI86fCNMcbazEtwE=
 google.golang.org/api v0.7.0/go.mod h1:WtwebWUNSVBH/HAw79HIFXZNqEvBhG+Ra+ax0hx3E3M=
 google.golang.org/api v0.8.0/go.mod h1:o4eAsZoiT+ibD93RtjEohWalFOjRDx6CVaqeizhEnKg=
@@ -1509,8 +1522,8 @@ modernc.org/opt v0.1.4 h1:2kNGMRiUjrp4LcaPuLY2PzUfqM/w9N23quVwhKt5Qm8=
 modernc.org/opt v0.1.4/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
 modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
 modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
-modernc.org/sqlite v1.39.1 h1:H+/wGFzuSCIEVCvXYVHX5RQglwhMOvtHSv+VtidL2r4=
-modernc.org/sqlite v1.39.1/go.mod h1:9fjQZ0mB1LLP0GYrp39oOJXx/I2sxEnZtzCmEQIKvGE=
+modernc.org/sqlite v1.40.0 h1:bNWEDlYhNPAUdUdBzjAvn8icAs/2gaKlj4vM+tQ6KdQ=
+modernc.org/sqlite v1.40.0/go.mod h1:9fjQZ0mB1LLP0GYrp39oOJXx/I2sxEnZtzCmEQIKvGE=
 modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
 modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
 modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=

internal/capabilities/pkgtestobservation/model.go

@@ -0,0 +1,46 @@
+package pkgtestobservation
+
+import "time"
+
+// Observations represents capability observations during testing
+type Observations struct {
+	License       bool         `json:"license"`
+	Relationships Relationship `json:"relationships"`
+	FileListing   Count        `json:"file_listing"`
+	FileDigests   Count        `json:"file_digests"`
+	IntegrityHash Count        `json:"integrity_hash"`
+}
+
+// Relationship tracks dependency relationship observations
+type Relationship struct {
+	Found bool `json:"found"`
+	Count int  `json:"count"`
+}
+
+// Count tracks whether a capability was found and how many times
+type Count struct {
+	Found bool `json:"found"`
+	Count int  `json:"count"`
+}
+
+// Test is the root structure for test-observations.json
+type Test struct {
+	Package    string                `json:"package"`
+	UpdatedAt  time.Time             `json:"updated_at"`
+	Catalogers map[string]*Cataloger `json:"catalogers"`
+	Parsers    map[string]*Parser    `json:"parsers"`
+}
+
+// Parser captures all observations for a parser
+type Parser struct {
+	MetadataTypes []string     `json:"metadata_types"`
+	PackageTypes  []string     `json:"package_types"`
+	Observations  Observations `json:"observations"`
+}
+
+// Cataloger captures all observations for a cataloger
+type Cataloger struct {
+	MetadataTypes []string     `json:"metadata_types"`
+	PackageTypes  []string     `json:"package_types"`
+	Observations  Observations `json:"observations"`
+}

internal/constants.go

@@ -3,5 +3,9 @@ package internal
 const (
 	// JSONSchemaVersion is the current schema version output by the JSON encoder
 	// This is roughly following the "SchemaVer" guidelines for versioning the JSON schema. Please see schema/json/README.md for details on how to increment.
-	JSONSchemaVersion = "16.0.40"
+	JSONSchemaVersion = "16.1.0"
+
+	// Changelog
+	// 16.1.0 - reformulated the python pdm fields (added "URL" and removed the unused "path" field).
+
 )

internal/file/tar_file_traversal.go

@@ -1,17 +1,40 @@
 package file
 
 import (
+	"context"
 	"fmt"
 	"os"
 	"path/filepath"
 
 	"github.com/bmatcuk/doublestar/v4"
+	"github.com/mholt/archives"
 
-	"github.com/anchore/archiver/v3"
+	"github.com/anchore/syft/internal"
 )
 
+// TraverseFilesInTar enumerates all paths stored within a tar archive using the visitor pattern.
+func TraverseFilesInTar(ctx context.Context, archivePath string, visitor archives.FileHandler) error {
+	tarReader, err := os.Open(archivePath)
+	if err != nil {
+		return fmt.Errorf("unable to open tar archive (%s): %w", archivePath, err)
+	}
+	defer internal.CloseAndLogError(tarReader, archivePath)
+
+	format, _, err := archives.Identify(ctx, archivePath, nil)
+	if err != nil {
+		return fmt.Errorf("failed to identify tar compression format: %w", err)
+	}
+
+	extractor, ok := format.(archives.Extractor)
+	if !ok {
+		return fmt.Errorf("file format does not support extraction: %s", archivePath)
+	}
+
+	return extractor.Extract(ctx, tarReader, visitor)
+}
+
 // ExtractGlobsFromTarToUniqueTempFile extracts paths matching the given globs within the given archive to a temporary directory, returning file openers for each file extracted.
-func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...string) (map[string]Opener, error) {
+func ExtractGlobsFromTarToUniqueTempFile(ctx context.Context, archivePath, dir string, globs ...string) (map[string]Opener, error) {
 	results := make(map[string]Opener)
 
 	// don't allow for full traversal, only select traversal from given paths
@@ -19,9 +42,7 @@ func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...strin
 		return results, nil
 	}
 
-	visitor := func(file archiver.File) error {
-		defer file.Close()
-
+	visitor := func(_ context.Context, file archives.FileInfo) error {
 		// ignore directories
 		if file.IsDir() {
 			return nil
@@ -43,7 +64,13 @@ func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...strin
 		// provides a ReadCloser. It is up to the caller to handle closing the file explicitly.
 		defer tempFile.Close()
 
-		if err := safeCopy(tempFile, file.ReadCloser); err != nil {
+		packedFile, err := file.Open()
+		if err != nil {
+			return fmt.Errorf("unable to read file=%q from tar=%q: %w", file.NameInArchive, archivePath, err)
+		}
+		defer internal.CloseAndLogError(packedFile, archivePath)
+
+		if err := safeCopy(tempFile, packedFile); err != nil {
 			return fmt.Errorf("unable to copy source=%q for tar=%q: %w", file.Name(), archivePath, err)
 		}
 
@@ -52,7 +79,7 @@ func ExtractGlobsFromTarToUniqueTempFile(archivePath, dir string, globs ...strin
 		return nil
 	}
 
-	return results, archiver.Walk(archivePath, visitor)
+	return results, TraverseFilesInTar(ctx, archivePath, visitor)
 }
 
 func matchesAnyGlob(name string, globs ...string) bool {

internal/file/zip_file_manifest.go

@@ -1,10 +1,12 @@
 package file
 
 import (
+	"context"
 	"os"
 	"sort"
 	"strings"
 
+	"github.com/mholt/archives"
 	"github.com/scylladb/go-set/strset"
 
 	"github.com/anchore/syft/internal/log"
@@ -14,22 +16,25 @@ import (
 type ZipFileManifest map[string]os.FileInfo
 
 // NewZipFileManifest creates and returns a new ZipFileManifest populated with path and metadata from the given zip archive path.
-func NewZipFileManifest(archivePath string) (ZipFileManifest, error) {
-	zipReader, err := OpenZip(archivePath)
+func NewZipFileManifest(ctx context.Context, archivePath string) (ZipFileManifest, error) {
+	zipReader, err := os.Open(archivePath)
 	manifest := make(ZipFileManifest)
 	if err != nil {
 		log.Debugf("unable to open zip archive (%s): %v", archivePath, err)
 		return manifest, err
 	}
 	defer func() {
-		err = zipReader.Close()
-		if err != nil {
+		if err = zipReader.Close(); err != nil {
 			log.Debugf("unable to close zip archive (%s): %+v", archivePath, err)
 		}
 	}()
 
-	for _, file := range zipReader.File {
-		manifest.Add(file.Name, file.FileInfo())
+	err = archives.Zip{}.Extract(ctx, zipReader, func(_ context.Context, file archives.FileInfo) error {
+		manifest.Add(file.NameInArchive, file.FileInfo)
+		return nil
+	})
+	if err != nil {
+		return manifest, err
 	}
 	return manifest, nil
 }

internal/file/zip_file_manifest_test.go

@@ -4,6 +4,7 @@
 package file
 
 import (
+	"context"
 	"encoding/json"
 	"os"
 	"path"
@@ -24,7 +25,7 @@ func TestNewZipFileManifest(t *testing.T) {
 
 	archiveFilePath := setupZipFileTest(t, sourceDirPath, false)
 
-	actual, err := NewZipFileManifest(archiveFilePath)
+	actual, err := NewZipFileManifest(context.Background(), archiveFilePath)
 	if err != nil {
 		t.Fatalf("unable to extract from unzip archive: %+v", err)
 	}
@@ -59,7 +60,7 @@ func TestNewZip64FileManifest(t *testing.T) {
 	sourceDirPath := path.Join(cwd, "test-fixtures", "zip-source")
 	archiveFilePath := setupZipFileTest(t, sourceDirPath, true)
 
-	actual, err := NewZipFileManifest(archiveFilePath)
+	actual, err := NewZipFileManifest(context.Background(), archiveFilePath)
 	if err != nil {
 		t.Fatalf("unable to extract from unzip archive: %+v", err)
 	}
@@ -99,7 +100,7 @@ func TestZipFileManifest_GlobMatch(t *testing.T) {
 
 	archiveFilePath := setupZipFileTest(t, sourceDirPath, false)
 
-	z, err := NewZipFileManifest(archiveFilePath)
+	z, err := NewZipFileManifest(context.Background(), archiveFilePath)
 	if err != nil {
 		t.Fatalf("unable to extract from unzip archive: %+v", err)
 	}

internal/file/zip_file_traversal.go

@@ -1,13 +1,15 @@
 package file
 
 import (
-	"archive/zip"
 	"bytes"
+	"context"
 	"fmt"
 	"os"
 	"path/filepath"
 	"strings"
 
+	"github.com/mholt/archives"
+
 	"github.com/anchore/syft/internal/log"
 )
 
@@ -25,7 +27,7 @@ type errZipSlipDetected struct {
 }
 
 func (e *errZipSlipDetected) Error() string {
-	return fmt.Sprintf("paths are not allowed to resolve outside of the root prefix (%q). Destination: %q", e.Prefix, e.JoinArgs)
+	return fmt.Sprintf("path traversal detected: paths are not allowed to resolve outside of the root prefix (%q). Destination: %q", e.Prefix, e.JoinArgs)
 }
 
 type zipTraversalRequest map[string]struct{}
@@ -39,38 +41,34 @@ func newZipTraverseRequest(paths ...string) zipTraversalRequest {
 }
 
 // TraverseFilesInZip enumerates all paths stored within a zip archive using the visitor pattern.
-func TraverseFilesInZip(archivePath string, visitor func(*zip.File) error, paths ...string) error {
+func TraverseFilesInZip(ctx context.Context, archivePath string, visitor archives.FileHandler, paths ...string) error {
 	request := newZipTraverseRequest(paths...)
 
-	zipReader, err := OpenZip(archivePath)
+	zipReader, err := os.Open(archivePath)
 	if err != nil {
 		return fmt.Errorf("unable to open zip archive (%s): %w", archivePath, err)
 	}
 	defer func() {
-		err = zipReader.Close()
-		if err != nil {
+		if err := zipReader.Close(); err != nil {
 			log.Errorf("unable to close zip archive (%s): %+v", archivePath, err)
 		}
 	}()
 
-	for _, file := range zipReader.File {
+	return archives.Zip{}.Extract(ctx, zipReader, func(ctx context.Context, file archives.FileInfo) error {
 		// if no paths are given then assume that all files should be traversed
 		if len(paths) > 0 {
-			if _, ok := request[file.Name]; !ok {
+			if _, ok := request[file.NameInArchive]; !ok {
 				// this file path is not of interest
-				continue
+				return nil
 			}
 		}
 
-		if err = visitor(file); err != nil {
-			return err
-		}
-	}
-	return nil
+		return visitor(ctx, file)
+	})
 }
 
 // ExtractFromZipToUniqueTempFile extracts select paths for the given archive to a temporary directory, returning file openers for each file extracted.
-func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (map[string]Opener, error) {
+func ExtractFromZipToUniqueTempFile(ctx context.Context, archivePath, dir string, paths ...string) (map[string]Opener, error) {
 	results := make(map[string]Opener)
 
 	// don't allow for full traversal, only select traversal from given paths
@@ -78,9 +76,8 @@ func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (m
 		return results, nil
 	}
 
-	visitor := func(file *zip.File) error {
-		tempfilePrefix := filepath.Base(filepath.Clean(file.Name)) + "-"
-
+	visitor := func(_ context.Context, file archives.FileInfo) error {
+		tempfilePrefix := filepath.Base(filepath.Clean(file.NameInArchive)) + "-"
 		tempFile, err := os.CreateTemp(dir, tempfilePrefix)
 		if err != nil {
 			return fmt.Errorf("unable to create temp file: %w", err)
@@ -92,33 +89,32 @@ func ExtractFromZipToUniqueTempFile(archivePath, dir string, paths ...string) (m
 
 		zippedFile, err := file.Open()
 		if err != nil {
-			return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.NameInArchive, archivePath, err)
 		}
 		defer func() {
-			err := zippedFile.Close()
-			if err != nil {
-				log.Errorf("unable to close source file=%q from zip=%q: %+v", file.Name, archivePath, err)
+			if err := zippedFile.Close(); err != nil {
+				log.Errorf("unable to close source file=%q from zip=%q: %+v", file.NameInArchive, archivePath, err)
 			}
 		}()
 
-		if file.FileInfo().IsDir() {
-			return fmt.Errorf("unable to extract directories, only files: %s", file.Name)
+		if file.IsDir() {
+			return fmt.Errorf("unable to extract directories, only files: %s", file.NameInArchive)
 		}
 
 		if err := safeCopy(tempFile, zippedFile); err != nil {
-			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", file.NameInArchive, archivePath, err)
 		}
 
-		results[file.Name] = Opener{path: tempFile.Name()}
+		results[file.NameInArchive] = Opener{path: tempFile.Name()}
 
 		return nil
 	}
 
-	return results, TraverseFilesInZip(archivePath, visitor, paths...)
+	return results, TraverseFilesInZip(ctx, archivePath, visitor, paths...)
 }
 
 // ContentsFromZip extracts select paths for the given archive and returns a set of string contents for each path.
-func ContentsFromZip(archivePath string, paths ...string) (map[string]string, error) {
+func ContentsFromZip(ctx context.Context, archivePath string, paths ...string) (map[string]string, error) {
 	results := make(map[string]string)
 
 	// don't allow for full traversal, only select traversal from given paths
@@ -126,37 +122,38 @@ func ContentsFromZip(archivePath string, paths ...string) (map[string]string, er
 		return results, nil
 	}
 
-	visitor := func(file *zip.File) error {
+	visitor := func(_ context.Context, file archives.FileInfo) error {
 		zippedFile, err := file.Open()
 		if err != nil {
-			return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.NameInArchive, archivePath, err)
 		}
+		defer func() {
+			if err := zippedFile.Close(); err != nil {
+				log.Errorf("unable to close source file=%q from zip=%q: %+v", file.NameInArchive, archivePath, err)
+			}
+		}()
 
-		if file.FileInfo().IsDir() {
-			return fmt.Errorf("unable to extract directories, only files: %s", file.Name)
+		if file.IsDir() {
+			return fmt.Errorf("unable to extract directories, only files: %s", file.NameInArchive)
 		}
 
 		var buffer bytes.Buffer
 		if err := safeCopy(&buffer, zippedFile); err != nil {
-			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", file.Name, archivePath, err)
+			return fmt.Errorf("unable to copy source=%q for zip=%q: %w", file.NameInArchive, archivePath, err)
 		}
 
-		results[file.Name] = buffer.String()
+		results[file.NameInArchive] = buffer.String()
 
-		err = zippedFile.Close()
-		if err != nil {
-			return fmt.Errorf("unable to close source file=%q from zip=%q: %w", file.Name, archivePath, err)
-		}
 		return nil
 	}
 
-	return results, TraverseFilesInZip(archivePath, visitor, paths...)
+	return results, TraverseFilesInZip(ctx, archivePath, visitor, paths...)
 }
 
 // UnzipToDir extracts a zip archive to a target directory.
-func UnzipToDir(archivePath, targetDir string) error {
-	visitor := func(file *zip.File) error {
-		joinedPath, err := safeJoin(targetDir, file.Name)
+func UnzipToDir(ctx context.Context, archivePath, targetDir string) error {
+	visitor := func(_ context.Context, file archives.FileInfo) error {
+		joinedPath, err := SafeJoin(targetDir, file.NameInArchive)
 		if err != nil {
 			return err
 		}
@@ -164,11 +161,11 @@ func UnzipToDir(archivePath, targetDir string) error {
 		return extractSingleFile(file, joinedPath, archivePath)
 	}
 
-	return TraverseFilesInZip(archivePath, visitor)
+	return TraverseFilesInZip(ctx, archivePath, visitor)
 }
 
-// safeJoin ensures that any destinations do not resolve to a path above the prefix path.
-func safeJoin(prefix string, dest ...string) (string, error) {
+// SafeJoin ensures that any destinations do not resolve to a path above the prefix path.
+func SafeJoin(prefix string, dest ...string) (string, error) {
 	joinResult := filepath.Join(append([]string{prefix}, dest...)...)
 	cleanJoinResult := filepath.Clean(joinResult)
 	if !strings.HasPrefix(cleanJoinResult, filepath.Clean(prefix)) {
@@ -181,13 +178,18 @@ func safeJoin(prefix string, dest ...string) (string, error) {
 	return joinResult, nil
 }
 
-func extractSingleFile(file *zip.File, expandedFilePath, archivePath string) error {
+func extractSingleFile(file archives.FileInfo, expandedFilePath, archivePath string) error {
 	zippedFile, err := file.Open()
 	if err != nil {
-		return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.Name, archivePath, err)
+		return fmt.Errorf("unable to read file=%q from zip=%q: %w", file.NameInArchive, archivePath, err)
 	}
+	defer func() {
+		if err := zippedFile.Close(); err != nil {
+			log.Errorf("unable to close source file=%q from zip=%q: %+v", file.NameInArchive, archivePath, err)
+		}
+	}()
 
-	if file.FileInfo().IsDir() {
+	if file.IsDir() {
 		err = os.MkdirAll(expandedFilePath, file.Mode())
 		if err != nil {
 			return fmt.Errorf("unable to create dir=%q from zip=%q: %w", expandedFilePath, archivePath, err)
@@ -202,20 +204,16 @@ func extractSingleFile(file *zip.File, expandedFilePath, archivePath string) err
 		if err != nil {
 			return fmt.Errorf("unable to create dest file=%q from zip=%q: %w", expandedFilePath, archivePath, err)
 		}
+		defer func() {
+			if err := outputFile.Close(); err != nil {
+				log.Errorf("unable to close dest file=%q from zip=%q: %+v", outputFile.Name(), archivePath, err)
+			}
+		}()
 
 		if err := safeCopy(outputFile, zippedFile); err != nil {
-			return fmt.Errorf("unable to copy source=%q to dest=%q for zip=%q: %w", file.Name, outputFile.Name(), archivePath, err)
-		}
-
-		err = outputFile.Close()
-		if err != nil {
-			return fmt.Errorf("unable to close dest file=%q from zip=%q: %w", outputFile.Name(), archivePath, err)
+			return fmt.Errorf("unable to copy source=%q to dest=%q for zip=%q: %w", file.NameInArchive, outputFile.Name(), archivePath, err)
 		}
 	}
 
-	err = zippedFile.Close()
-	if err != nil {
-		return fmt.Errorf("unable to close source file=%q from zip=%q: %w", file.Name, archivePath, err)
-	}
 	return nil
 }

internal/file/zip_file_traversal_test.go

@@ -4,6 +4,8 @@
 package file
 
 import (
+	"archive/zip"
+	"context"
 	"crypto/sha256"
 	"encoding/json"
 	"errors"
@@ -17,6 +19,7 @@ import (
 
 	"github.com/go-test/deep"
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 )
 
 func equal(r1, r2 io.Reader) (bool, error) {
@@ -55,7 +58,7 @@ func TestUnzipToDir(t *testing.T) {
 	expectedPaths := len(expectedZipArchiveEntries)
 	observedPaths := 0
 
-	err = UnzipToDir(archiveFilePath, unzipDestinationDir)
+	err = UnzipToDir(context.Background(), archiveFilePath, unzipDestinationDir)
 	if err != nil {
 		t.Fatalf("unable to unzip archive: %+v", err)
 	}
@@ -145,7 +148,7 @@ func TestContentsFromZip(t *testing.T) {
 				paths = append(paths, p)
 			}
 
-			actual, err := ContentsFromZip(archivePath, paths...)
+			actual, err := ContentsFromZip(context.Background(), archivePath, paths...)
 			if err != nil {
 				t.Fatalf("unable to extract from unzip archive: %+v", err)
 			}
@@ -307,9 +310,528 @@ func TestSafeJoin(t *testing.T) {
 
 	for _, test := range tests {
 		t.Run(fmt.Sprintf("%+v:%+v", test.prefix, test.args), func(t *testing.T) {
-			actual, err := safeJoin(test.prefix, test.args...)
+			actual, err := SafeJoin(test.prefix, test.args...)
 			test.errAssertion(t, err)
 			assert.Equal(t, test.expected, actual)
 		})
 	}
 }
+
+// TestSymlinkProtection demonstrates that SafeJoin protects against symlink-based
+// directory traversal attacks by validating that archive entry paths cannot escape
+// the extraction directory.
+func TestSafeJoin_SymlinkProtection(t *testing.T) {
+	tests := []struct {
+		name        string
+		archivePath string // Path as it would appear in the archive
+		expectError bool
+		description string
+	}{
+		{
+			name:        "path traversal via ../",
+			archivePath: "../../../outside/file.txt",
+			expectError: true,
+			description: "Archive entry with ../ trying to escape extraction dir",
+		},
+		{
+			name:        "absolute path symlink target",
+			archivePath: "../../../sensitive.txt",
+			expectError: true,
+			description: "Simulates symlink pointing outside via relative path",
+		},
+		{
+			name:        "safe relative path within extraction dir",
+			archivePath: "subdir/safe.txt",
+			expectError: false,
+			description: "Normal file path that stays within extraction directory",
+		},
+		{
+			name:        "safe path with internal ../",
+			archivePath: "dir1/../dir2/file.txt",
+			expectError: false,
+			description: "Path with ../ that still resolves within extraction dir",
+		},
+		{
+			name:        "deeply nested traversal",
+			archivePath: "../../../../../../tmp/evil.txt",
+			expectError: true,
+			description: "Multiple levels of ../ trying to escape",
+		},
+		{
+			name:        "single parent directory escape",
+			archivePath: "../",
+			expectError: true,
+			description: "Simple one-level escape attempt",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Create temp directories to simulate extraction scenario
+			tmpDir := t.TempDir()
+			extractDir := filepath.Join(tmpDir, "extract")
+			outsideDir := filepath.Join(tmpDir, "outside")
+
+			require.NoError(t, os.MkdirAll(extractDir, 0755))
+			require.NoError(t, os.MkdirAll(outsideDir, 0755))
+
+			// Create a file outside extraction dir that an attacker might target
+			outsideFile := filepath.Join(outsideDir, "sensitive.txt")
+			require.NoError(t, os.WriteFile(outsideFile, []byte("sensitive data"), 0644))
+
+			// Test SafeJoin - this is what happens when processing archive entries
+			result, err := SafeJoin(extractDir, tt.archivePath)
+
+			if tt.expectError {
+				// Should block malicious paths
+				require.Error(t, err, "Expected SafeJoin to reject malicious path")
+				var zipSlipErr *errZipSlipDetected
+				assert.ErrorAs(t, err, &zipSlipErr, "Error should be errZipSlipDetected type")
+				assert.Empty(t, result, "Result should be empty for blocked paths")
+			} else {
+				// Should allow safe paths
+				require.NoError(t, err, "Expected SafeJoin to allow safe path")
+				assert.NotEmpty(t, result, "Result should not be empty for safe paths")
+				assert.True(t, strings.HasPrefix(filepath.Clean(result), filepath.Clean(extractDir)),
+					"Safe path should resolve within extraction directory")
+			}
+		})
+	}
+}
+
+// TestUnzipToDir_SymlinkAttacks tests UnzipToDir function with malicious ZIP archives
+// containing symlink entries that attempt path traversal attacks.
+//
+// EXPECTED BEHAVIOR: UnzipToDir should either:
+//  1. Detect and reject symlinks explicitly with a security error, OR
+//  2. Extract them safely (library converts symlinks to regular files)
+func TestUnzipToDir_SymlinkAttacks(t *testing.T) {
+	tests := []struct {
+		name        string
+		symlinkName string
+		fileName    string
+		errContains string
+	}{
+		{
+			name:        "direct symlink to outside directory",
+			symlinkName: "evil_link",
+			fileName:    "evil_link/payload.txt",
+			errContains: "not a directory", // attempt to write through symlink leaf (which is not a directory)
+		},
+		{
+			name:        "directory symlink attack",
+			symlinkName: "safe_dir/link",
+			fileName:    "safe_dir/link/payload.txt",
+			errContains: "not a directory", // attempt to write through symlink (which is not a directory)
+		},
+		{
+			name:        "symlink without payload file",
+			symlinkName: "standalone_link",
+			fileName:    "", // no payload file
+			errContains: "", // no error expected, symlink without payload is safe
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			tempDir := t.TempDir()
+
+			// create outside target directory
+			outsideDir := filepath.Join(tempDir, "outside_target")
+			require.NoError(t, os.MkdirAll(outsideDir, 0755))
+
+			// create extraction directory
+			extractDir := filepath.Join(tempDir, "extract")
+			require.NoError(t, os.MkdirAll(extractDir, 0755))
+
+			maliciousZip := createMaliciousZipWithSymlink(t, tempDir, tt.symlinkName, outsideDir, tt.fileName)
+
+			err := UnzipToDir(context.Background(), maliciousZip, extractDir)
+
+			// check error expectations
+			if tt.errContains != "" {
+				require.Error(t, err)
+				require.Contains(t, err.Error(), tt.errContains)
+			} else {
+				require.NoError(t, err)
+			}
+
+			analyzeExtractionDirectory(t, extractDir)
+
+			// check if payload file escaped extraction directory
+			if tt.fileName != "" {
+				maliciousFile := filepath.Join(outsideDir, filepath.Base(tt.fileName))
+				checkFileOutsideExtraction(t, maliciousFile)
+			}
+
+			// check if symlink was created pointing outside
+			symlinkPath := filepath.Join(extractDir, tt.symlinkName)
+			checkSymlinkCreation(t, symlinkPath, extractDir, outsideDir)
+		})
+	}
+}
+
+// TestContentsFromZip_SymlinkAttacks tests the ContentsFromZip function with malicious
+// ZIP archives containing symlink entries.
+//
+// EXPECTED BEHAVIOR: ContentsFromZip should either:
+//  1. Reject symlinks explicitly, OR
+//  2. Return empty content for symlinks (library behavior)
+//
+// Though ContentsFromZip doesn't write to disk, but if symlinks are followed, it could read sensitive
+// files from outside the archive.
+func TestContentsFromZip_SymlinkAttacks(t *testing.T) {
+	tests := []struct {
+		name          string
+		symlinkName   string
+		symlinkTarget string
+		requestPath   string
+		errContains   string
+	}{
+		{
+			name:          "request symlink entry directly",
+			symlinkName:   "evil_link",
+			symlinkTarget: "/etc/hosts", // attempt to read sensitive file
+			requestPath:   "evil_link",
+			errContains:   "", // no error expected - library returns symlink metadata
+		},
+		{
+			name:          "symlink in nested directory",
+			symlinkName:   "nested/link",
+			symlinkTarget: "/etc/hosts",
+			requestPath:   "nested/link",
+			errContains:   "", // no error expected - library returns symlink metadata
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			tempDir := t.TempDir()
+
+			// create malicious ZIP with symlink entry (no payload file needed)
+			maliciousZip := createMaliciousZipWithSymlink(t, tempDir, tt.symlinkName, tt.symlinkTarget, "")
+
+			contents, err := ContentsFromZip(context.Background(), maliciousZip, tt.requestPath)
+
+			// check error expectations
+			if tt.errContains != "" {
+				require.Error(t, err)
+				require.Contains(t, err.Error(), tt.errContains)
+				return
+			}
+			require.NoError(t, err)
+
+			// verify symlink handling - library should return symlink target as content (metadata)
+			content, found := contents[tt.requestPath]
+			require.True(t, found, "symlink entry should be found in results")
+
+			// verify symlink was NOT followed (content should be target path or empty)
+			if content != "" && content != tt.symlinkTarget {
+				// content is not empty and not the symlink target - check if actual file was read
+				if _, statErr := os.Stat(tt.symlinkTarget); statErr == nil {
+					targetContent, readErr := os.ReadFile(tt.symlinkTarget)
+					if readErr == nil && string(targetContent) == content {
+						t.Errorf("critical issue!... symlink was FOLLOWED and external file content was read!")
+						t.Logf("  symlink: %s → %s", tt.requestPath, tt.symlinkTarget)
+						t.Logf("  content length: %d bytes", len(content))
+					}
+				}
+			}
+		})
+	}
+}
+
+// TestExtractFromZipToUniqueTempFile_SymlinkAttacks tests the ExtractFromZipToUniqueTempFile
+// function with malicious ZIP archives containing symlink entries.
+//
+// EXPECTED BEHAVIOR: ExtractFromZipToUniqueTempFile should either:
+//  1. Reject symlinks explicitly, OR
+//  2. Extract them safely (library converts to empty files, filepath.Base sanitizes names)
+//
+// This function uses filepath.Base() on the archive entry name for temp file prefix and
+// os.CreateTemp() which creates files in the specified directory, so it should be protected.
+func TestExtractFromZipToUniqueTempFile_SymlinkAttacks(t *testing.T) {
+	tests := []struct {
+		name          string
+		symlinkName   string
+		symlinkTarget string
+		requestPath   string
+		errContains   string
+	}{
+		{
+			name:          "extract symlink entry to temp file",
+			symlinkName:   "evil_link",
+			symlinkTarget: "/etc/passwd",
+			requestPath:   "evil_link",
+			errContains:   "", // no error expected - library extracts symlink metadata
+		},
+		{
+			name:          "extract nested symlink",
+			symlinkName:   "nested/dir/link",
+			symlinkTarget: "/tmp/outside",
+			requestPath:   "nested/dir/link",
+			errContains:   "", // no error expected
+		},
+		{
+			name:          "extract path traversal symlink name",
+			symlinkName:   "../../escape",
+			symlinkTarget: "/tmp/outside",
+			requestPath:   "../../escape",
+			errContains:   "", // no error expected - filepath.Base sanitizes name
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			tempDir := t.TempDir()
+
+			maliciousZip := createMaliciousZipWithSymlink(t, tempDir, tt.symlinkName, tt.symlinkTarget, "")
+
+			// create temp directory for extraction
+			extractTempDir := filepath.Join(tempDir, "temp_extract")
+			require.NoError(t, os.MkdirAll(extractTempDir, 0755))
+
+			openers, err := ExtractFromZipToUniqueTempFile(context.Background(), maliciousZip, extractTempDir, tt.requestPath)
+
+			// check error expectations
+			if tt.errContains != "" {
+				require.Error(t, err)
+				require.Contains(t, err.Error(), tt.errContains)
+				return
+			}
+			require.NoError(t, err)
+
+			// verify symlink was extracted
+			opener, found := openers[tt.requestPath]
+			require.True(t, found, "symlink entry should be extracted")
+
+			// verify temp file is within temp directory
+			tempFilePath := opener.path
+			cleanTempDir := filepath.Clean(extractTempDir)
+			cleanTempFile := filepath.Clean(tempFilePath)
+			require.True(t, strings.HasPrefix(cleanTempFile, cleanTempDir),
+				"temp file must be within temp directory: %s not in %s", cleanTempFile, cleanTempDir)
+
+			// verify symlink was NOT followed (content should be target path or empty)
+			f, openErr := opener.Open()
+			require.NoError(t, openErr)
+			defer f.Close()
+
+			content, readErr := io.ReadAll(f)
+			require.NoError(t, readErr)
+
+			// check if symlink was followed (content matches actual file)
+			if len(content) > 0 && string(content) != tt.symlinkTarget {
+				if _, statErr := os.Stat(tt.symlinkTarget); statErr == nil {
+					targetContent, readErr := os.ReadFile(tt.symlinkTarget)
+					if readErr == nil && string(targetContent) == string(content) {
+						t.Errorf("critical issue!... symlink was FOLLOWED and external file content was copied!")
+						t.Logf("  symlink: %s → %s", tt.requestPath, tt.symlinkTarget)
+						t.Logf("  content length: %d bytes", len(content))
+					}
+				}
+			}
+		})
+	}
+}
+
+// forensicFindings contains the results of analyzing an extraction directory
+type forensicFindings struct {
+	symlinksFound          []forensicSymlink
+	regularFiles           []string
+	directories            []string
+	symlinkVulnerabilities []string
+}
+
+type forensicSymlink struct {
+	path              string
+	target            string
+	escapesExtraction bool
+	resolvedPath      string
+}
+
+// analyzeExtractionDirectory walks the extraction directory and detects symlinks that point
+// outside the extraction directory. It is silent unless vulnerabilities are found.
+func analyzeExtractionDirectory(t *testing.T, extractDir string) forensicFindings {
+	t.Helper()
+
+	findings := forensicFindings{}
+
+	filepath.Walk(extractDir, func(path string, info os.FileInfo, err error) error {
+		if err != nil {
+			// only log if there's an error walking the directory
+			t.Logf("Error walking %s: %v", path, err)
+			return nil
+		}
+
+		relPath := strings.TrimPrefix(path, extractDir+"/")
+		if relPath == "" {
+			relPath = "."
+		}
+
+		// use Lstat to detect symlinks without following them
+		linfo, lerr := os.Lstat(path)
+		if lerr == nil && linfo.Mode()&os.ModeSymlink != 0 {
+			target, _ := os.Readlink(path)
+
+			// resolve to see where it actually points
+			var resolvedPath string
+			var escapesExtraction bool
+
+			if filepath.IsAbs(target) {
+				// absolute symlink
+				resolvedPath = target
+				cleanExtractDir := filepath.Clean(extractDir)
+				escapesExtraction = !strings.HasPrefix(filepath.Clean(target), cleanExtractDir)
+
+				if escapesExtraction {
+					t.Errorf("critical issue!... absolute symlink created: %s → %s", relPath, target)
+					t.Logf("  this symlink points outside the extraction directory")
+					findings.symlinkVulnerabilities = append(findings.symlinkVulnerabilities,
+						fmt.Sprintf("absolute symlink: %s → %s", relPath, target))
+				}
+			} else {
+				// relative symlink - resolve it
+				resolvedPath = filepath.Join(filepath.Dir(path), target)
+				cleanResolved := filepath.Clean(resolvedPath)
+				cleanExtractDir := filepath.Clean(extractDir)
+
+				escapesExtraction = !strings.HasPrefix(cleanResolved, cleanExtractDir)
+
+				if escapesExtraction {
+					t.Errorf("critical issue!... symlink escapes extraction dir: %s → %s", relPath, target)
+					t.Logf("  symlink resolves to: %s (outside extraction directory)", cleanResolved)
+					findings.symlinkVulnerabilities = append(findings.symlinkVulnerabilities,
+						fmt.Sprintf("relative symlink escape: %s → %s (resolves to %s)", relPath, target, cleanResolved))
+				}
+			}
+
+			findings.symlinksFound = append(findings.symlinksFound, forensicSymlink{
+				path:              relPath,
+				target:            target,
+				escapesExtraction: escapesExtraction,
+				resolvedPath:      resolvedPath,
+			})
+		} else {
+			// regular file or directory - collect silently
+			if info.IsDir() {
+				findings.directories = append(findings.directories, relPath)
+			} else {
+				findings.regularFiles = append(findings.regularFiles, relPath)
+			}
+		}
+		return nil
+	})
+
+	return findings
+}
+
+// checkFileOutsideExtraction checks if a file was written outside the extraction directory.
+// Returns true if the file exists (vulnerability), false otherwise. Silent on success.
+func checkFileOutsideExtraction(t *testing.T, filePath string) bool {
+	t.Helper()
+
+	if stat, err := os.Stat(filePath); err == nil {
+		content, _ := os.ReadFile(filePath)
+		t.Errorf("critical issue!... file written OUTSIDE extraction directory!")
+		t.Logf("  location: %s", filePath)
+		t.Logf("  size: %d bytes", stat.Size())
+		t.Logf("  content: %s", string(content))
+		t.Logf("  ...this means an attacker can write files to arbitrary locations on the filesystem")
+		return true
+	}
+	// no file found outside extraction directory...
+	return false
+}
+
+// checkSymlinkCreation verifies if a symlink was created at the expected path and reports
+// whether it points outside the extraction directory. Silent unless a symlink is found.
+func checkSymlinkCreation(t *testing.T, symlinkPath, extractDir, expectedTarget string) bool {
+	t.Helper()
+
+	if linfo, err := os.Lstat(symlinkPath); err == nil {
+		if linfo.Mode()&os.ModeSymlink != 0 {
+			target, _ := os.Readlink(symlinkPath)
+
+			if expectedTarget != "" && target == expectedTarget {
+				t.Errorf("critical issue!... symlink pointing outside extraction dir was created!")
+				t.Logf("  Symlink: %s → %s", symlinkPath, target)
+				return true
+			}
+
+			// Check if it escapes even if target doesn't match expected
+			if filepath.IsAbs(target) {
+				cleanExtractDir := filepath.Clean(extractDir)
+				if !strings.HasPrefix(filepath.Clean(target), cleanExtractDir) {
+					t.Errorf("critical issue!... absolute symlink escapes extraction dir!")
+					t.Logf("  symlink: %s → %s", symlinkPath, target)
+					return true
+				}
+			}
+		}
+		// if it exists but is not a symlink, that's good (attack was thwarted)...
+	}
+
+	return false
+}
+
+// createMaliciousZipWithSymlink creates a ZIP archive containing a symlink entry pointing to an arbitrary target,
+// followed by a file entry that attempts to write through that symlink.
+// returns the path to the created ZIP archive.
+func createMaliciousZipWithSymlink(t *testing.T, tempDir, symlinkName, symlinkTarget, fileName string) string {
+	t.Helper()
+
+	maliciousZip := filepath.Join(tempDir, "malicious.zip")
+	zipFile, err := os.Create(maliciousZip)
+	require.NoError(t, err)
+	defer zipFile.Close()
+
+	zw := zip.NewWriter(zipFile)
+
+	// create parent directories if the symlink is nested
+	if dir := filepath.Dir(symlinkName); dir != "." {
+		dirHeader := &zip.FileHeader{
+			Name:   dir + "/",
+			Method: zip.Store,
+		}
+		dirHeader.SetMode(os.ModeDir | 0755)
+		_, err = zw.CreateHeader(dirHeader)
+		require.NoError(t, err)
+	}
+
+	// create symlink entry pointing outside extraction directory
+	// note: ZIP format stores symlinks as regular files with the target path as content
+	symlinkHeader := &zip.FileHeader{
+		Name:   symlinkName,
+		Method: zip.Store,
+	}
+	symlinkHeader.SetMode(os.ModeSymlink | 0755)
+
+	symlinkWriter, err := zw.CreateHeader(symlinkHeader)
+	require.NoError(t, err)
+
+	// write the symlink target as the file content (this is how ZIP stores symlinks)
+	_, err = symlinkWriter.Write([]byte(symlinkTarget))
+	require.NoError(t, err)
+
+	// create file entry that will be written through the symlink
+	if fileName != "" {
+		payloadContent := []byte("MALICIOUS PAYLOAD - This should NOT be written outside extraction dir!")
+		payloadHeader := &zip.FileHeader{
+			Name:   fileName,
+			Method: zip.Deflate,
+		}
+		payloadHeader.SetMode(0644)
+
+		payloadWriter, err := zw.CreateHeader(payloadHeader)
+		require.NoError(t, err)
+
+		_, err = payloadWriter.Write(payloadContent)
+		require.NoError(t, err)
+	}
+
+	require.NoError(t, zw.Close())
+	require.NoError(t, zipFile.Close())
+
+	return maliciousZip
+}

internal/file/zip_read_closer.go

@@ -1,229 +0,0 @@
-package file
-
-import (
-	"archive/zip"
-	"encoding/binary"
-	"errors"
-	"fmt"
-	"io"
-	"math"
-	"os"
-
-	"github.com/anchore/syft/internal/log"
-)
-
-// directoryEndLen, readByf, directoryEnd, and findSignatureInBlock were copied from the golang stdlib, specifically:
-// - https://github.com/golang/go/blob/go1.16.4/src/archive/zip/struct.go
-// - https://github.com/golang/go/blob/go1.16.4/src/archive/zip/reader.go
-// findArchiveStartOffset is derived from the same stdlib utils, specifically the readDirectoryEnd function.
-
-const (
-	directoryEndLen         = 22
-	directory64LocLen       = 20
-	directory64EndLen       = 56
-	directory64LocSignature = 0x07064b50
-	directory64EndSignature = 0x06064b50
-)
-
-// ZipReadCloser is a drop-in replacement for zip.ReadCloser (from zip.OpenReader) that additionally considers zips
-// that have bytes prefixed to the front of the archive (common with self-extracting jars).
-type ZipReadCloser struct {
-	*zip.Reader
-	io.Closer
-}
-
-// OpenZip provides a ZipReadCloser for the given filepath.
-func OpenZip(filepath string) (*ZipReadCloser, error) {
-	f, err := os.Open(filepath)
-	if err != nil {
-		return nil, err
-	}
-	fi, err := f.Stat()
-	if err != nil {
-		f.Close()
-		return nil, err
-	}
-
-	// some archives may have bytes prepended to the front of the archive, such as with self executing JARs. We first
-	// need to find the start of the archive and keep track of this offset.
-	offset, err := findArchiveStartOffset(f, fi.Size())
-	if err != nil {
-		log.Debugf("cannot find beginning of zip archive=%q : %v", filepath, err)
-		return nil, err
-	}
-
-	if _, err := f.Seek(0, io.SeekStart); err != nil {
-		return nil, fmt.Errorf("unable to seek to beginning of archive: %w", err)
-	}
-
-	if offset > math.MaxInt64 {
-		return nil, fmt.Errorf("archive start offset too large: %v", offset)
-	}
-	offset64 := int64(offset)
-
-	size := fi.Size() - offset64
-
-	r, err := zip.NewReader(io.NewSectionReader(f, offset64, size), size)
-	if err != nil {
-		log.Debugf("unable to open ZipReadCloser @ %q: %v", filepath, err)
-		return nil, err
-	}
-
-	return &ZipReadCloser{
-		Reader: r,
-		Closer: f,
-	}, nil
-}
-
-type readBuf []byte
-
-func (b *readBuf) uint16() uint16 {
-	v := binary.LittleEndian.Uint16(*b)
-	*b = (*b)[2:]
-	return v
-}
-
-func (b *readBuf) uint32() uint32 {
-	v := binary.LittleEndian.Uint32(*b)
-	*b = (*b)[4:]
-	return v
-}
-
-func (b *readBuf) uint64() uint64 {
-	v := binary.LittleEndian.Uint64(*b)
-	*b = (*b)[8:]
-	return v
-}
-
-type directoryEnd struct {
-	diskNbr            uint32 // unused
-	dirDiskNbr         uint32 // unused
-	dirRecordsThisDisk uint64 // unused
-	directoryRecords   uint64
-	directorySize      uint64
-	directoryOffset    uint64 // relative to file
-}
-
-// note: this is derived from readDirectoryEnd within the archive/zip package
-func findArchiveStartOffset(r io.ReaderAt, size int64) (startOfArchive uint64, err error) {
-	// look for directoryEndSignature in the last 1k, then in the last 65k
-	var buf []byte
-	var directoryEndOffset int64
-	for i, bLen := range []int64{1024, 65 * 1024} {
-		if bLen > size {
-			bLen = size
-		}
-		buf = make([]byte, int(bLen))
-		if _, err := r.ReadAt(buf, size-bLen); err != nil && !errors.Is(err, io.EOF) {
-			return 0, err
-		}
-		if p := findSignatureInBlock(buf); p >= 0 {
-			buf = buf[p:]
-			directoryEndOffset = size - bLen + int64(p)
-			break
-		}
-		if i == 1 || bLen == size {
-			return 0, zip.ErrFormat
-		}
-	}
-
-	if buf == nil {
-		// we were unable to find the directoryEndSignature block
-		return 0, zip.ErrFormat
-	}
-
-	// read header into struct
-	b := readBuf(buf[4:]) // skip signature
-	d := &directoryEnd{
-		diskNbr:            uint32(b.uint16()),
-		dirDiskNbr:         uint32(b.uint16()),
-		dirRecordsThisDisk: uint64(b.uint16()),
-		directoryRecords:   uint64(b.uint16()),
-		directorySize:      uint64(b.uint32()),
-		directoryOffset:    uint64(b.uint32()),
-	}
-	// Calculate where the zip data actually begins
-
-	// These values mean that the file can be a zip64 file
-	if d.directoryRecords == 0xffff || d.directorySize == 0xffff || d.directoryOffset == 0xffffffff {
-		p, err := findDirectory64End(r, directoryEndOffset)
-		if err == nil && p >= 0 {
-			directoryEndOffset = p
-			err = readDirectory64End(r, p, d)
-		}
-		if err != nil {
-			return 0, err
-		}
-	}
-	startOfArchive = uint64(directoryEndOffset) - d.directorySize - d.directoryOffset
-
-	// Make sure directoryOffset points to somewhere in our file.
-	if d.directoryOffset >= uint64(size) {
-		return 0, zip.ErrFormat
-	}
-	return startOfArchive, nil
-}
-
-// findDirectory64End tries to read the zip64 locator just before the
-// directory end and returns the offset of the zip64 directory end if
-// found.
-func findDirectory64End(r io.ReaderAt, directoryEndOffset int64) (int64, error) {
-	locOffset := directoryEndOffset - directory64LocLen
-	if locOffset < 0 {
-		return -1, nil // no need to look for a header outside the file
-	}
-	buf := make([]byte, directory64LocLen)
-	if _, err := r.ReadAt(buf, locOffset); err != nil {
-		return -1, err
-	}
-	b := readBuf(buf)
-	if sig := b.uint32(); sig != directory64LocSignature {
-		return -1, nil
-	}
-	if b.uint32() != 0 { // number of the disk with the start of the zip64 end of central directory
-		return -1, nil // the file is not a valid zip64-file
-	}
-	p := b.uint64()      // relative offset of the zip64 end of central directory record
-	if b.uint32() != 1 { // total number of disks
-		return -1, nil // the file is not a valid zip64-file
-	}
-	return int64(p), nil
-}
-
-// readDirectory64End reads the zip64 directory end and updates the
-// directory end with the zip64 directory end values.
-func readDirectory64End(r io.ReaderAt, offset int64, d *directoryEnd) (err error) {
-	buf := make([]byte, directory64EndLen)
-	if _, err := r.ReadAt(buf, offset); err != nil {
-		return err
-	}
-
-	b := readBuf(buf)
-	if sig := b.uint32(); sig != directory64EndSignature {
-		return errors.New("could not read directory64End")
-	}
-
-	b = b[12:]                        // skip dir size, version and version needed (uint64 + 2x uint16)
-	d.diskNbr = b.uint32()            // number of this disk
-	d.dirDiskNbr = b.uint32()         // number of the disk with the start of the central directory
-	d.dirRecordsThisDisk = b.uint64() // total number of entries in the central directory on this disk
-	d.directoryRecords = b.uint64()   // total number of entries in the central directory
-	d.directorySize = b.uint64()      // size of the central directory
-	d.directoryOffset = b.uint64()    // offset of start of central directory with respect to the starting disk number
-
-	return nil
-}
-
-func findSignatureInBlock(b []byte) int {
-	for i := len(b) - directoryEndLen; i >= 0; i-- {
-		// defined from directoryEndSignature
-		if b[i] == 'P' && b[i+1] == 'K' && b[i+2] == 0x05 && b[i+3] == 0x06 {
-			// n is length of comment
-			n := int(b[i+directoryEndLen-2]) | int(b[i+directoryEndLen-1])<<8
-			if n+directoryEndLen+i <= len(b) {
-				return i
-			}
-		}
-	}
-	return -1
-}

internal/file/zip_read_closer_test.go

@@ -1,50 +0,0 @@
-//go:build !windows
-// +build !windows
-
-package file
-
-import (
-	"os"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-func TestFindArchiveStartOffset(t *testing.T) {
-	tests := []struct {
-		name        string
-		archivePrep func(tb testing.TB) string
-		expected    uint64
-	}{
-		{
-			name:        "standard, non-nested zip",
-			archivePrep: prepZipSourceFixture,
-			expected:    0,
-		},
-		{
-			name:        "zip with prepended bytes",
-			archivePrep: prependZipSourceFixtureWithString(t, "junk at the beginning of the file..."),
-			expected:    36,
-		},
-	}
-
-	for _, test := range tests {
-		t.Run(test.name, func(t *testing.T) {
-			archivePath := test.archivePrep(t)
-			f, err := os.Open(archivePath)
-			if err != nil {
-				t.Fatalf("could not open archive %q: %+v", archivePath, err)
-			}
-			fi, err := os.Stat(f.Name())
-			if err != nil {
-				t.Fatalf("unable to stat archive: %+v", err)
-			}
-
-			actual, err := findArchiveStartOffset(f, fi.Size())
-			if err != nil {
-				t.Fatalf("unable to find offset: %+v", err)
-			}
-			assert.Equal(t, test.expected, actual)
-		})
-	}
-}

internal/os/feature_detection_test.go

@@ -81,6 +81,10 @@ func Test_EnvironmentTask(t *testing.T) {
 			// get the source
 			theSource, err := syft.GetSource(context.Background(), tarPath, syft.DefaultGetSourceConfig().WithSources("docker-archive"))
 			require.NoError(t, err)
+			t.Cleanup(func() {
+				require.NoError(t, theSource.Close())
+			})
+
 			resolver, err := theSource.FileResolver(source.SquashedScope)
 			require.NoError(t, err)
 

internal/packagemetadata/generated.go

@@ -27,6 +27,7 @@ func AllTypes() []any {
 		pkg.ELFBinaryPackageNoteJSONPayload{},
 		pkg.ElixirMixLockEntry{},
 		pkg.ErlangRebarLockEntry{},
+		pkg.GGUFFileHeader{},
 		pkg.GitHubActionsUseStatement{},
 		pkg.GolangBinaryBuildinfoEntry{},
 		pkg.GolangModuleEntry{},
@@ -49,8 +50,10 @@ func AllTypes() []any {
 		pkg.PhpComposerLockEntry{},
 		pkg.PhpPearEntry{},
 		pkg.PhpPeclEntry{},
+		pkg.PnpmLockEntry{},
 		pkg.PortageEntry{},
 		pkg.PythonPackage{},
+		pkg.PythonPdmLockEntry{},
 		pkg.PythonPipfileLockEntry{},
 		pkg.PythonPoetryLockEntry{},
 		pkg.PythonRequirementsEntry{},

internal/packagemetadata/names.go

@@ -95,13 +95,15 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.NpmPackage{}, "javascript-npm-package", "NpmPackageJsonMetadata"),
 	jsonNames(pkg.NpmPackageLockEntry{}, "javascript-npm-package-lock-entry", "NpmPackageLockJsonMetadata"),
 	jsonNames(pkg.YarnLockEntry{}, "javascript-yarn-lock-entry", "YarnLockJsonMetadata"),
+	jsonNames(pkg.PnpmLockEntry{}, "javascript-pnpm-lock-entry"),
 	jsonNames(pkg.PEBinary{}, "pe-binary"),
 	jsonNames(pkg.PhpComposerLockEntry{}, "php-composer-lock-entry", "PhpComposerJsonMetadata"),
 	jsonNamesWithoutLookup(pkg.PhpComposerInstalledEntry{}, "php-composer-installed-entry", "PhpComposerJsonMetadata"), // the legacy value is split into two types, where the other is preferred
-	jsonNames(pkg.PhpPeclEntry{}, "php-pecl-entry", "PhpPeclMetadata"),
+	jsonNames(pkg.PhpPeclEntry{}, "php-pecl-entry", "PhpPeclMetadata"),                                                 //nolint:staticcheck
 	jsonNames(pkg.PhpPearEntry{}, "php-pear-entry"),
 	jsonNames(pkg.PortageEntry{}, "portage-db-entry", "PortageMetadata"),
 	jsonNames(pkg.PythonPackage{}, "python-package", "PythonPackageMetadata"),
+	jsonNames(pkg.PythonPdmLockEntry{}, "python-pdm-lock-entry"),
 	jsonNames(pkg.PythonPipfileLockEntry{}, "python-pipfile-lock-entry", "PythonPipfileLockMetadata"),
 	jsonNames(pkg.PythonPoetryLockEntry{}, "python-poetry-lock-entry", "PythonPoetryLockMetadata"),
 	jsonNames(pkg.PythonRequirementsEntry{}, "python-pip-requirements-entry", "PythonRequirementsMetadata"),
@@ -122,6 +124,7 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.TerraformLockProviderEntry{}, "terraform-lock-provider-entry"),
 	jsonNames(pkg.DotnetPackagesLockEntry{}, "dotnet-packages-lock-entry"),
 	jsonNames(pkg.CondaMetaPackage{}, "conda-metadata-entry", "CondaPackageMetadata"),
+	jsonNames(pkg.GGUFFileHeader{}, "gguf-file-header"),
 )
 
 func expandLegacyNameVariants(names ...string) []string {

internal/spdxlicense/generate/generate_license_list.go

@@ -10,7 +10,6 @@ import (
 	"sort"
 	"strings"
 	"text/template"
-	"time"
 )
 
 // This program generates license_list.go.
@@ -20,8 +19,7 @@ const (
 )
 
 var tmp = template.Must(template.New("").Parse(`// Code generated by go generate; DO NOT EDIT.
-// This file was generated by robots at {{ .Timestamp }}
-// using data from {{ .URL }}
+// This file was generated using data from {{ .URL }}
 package spdxlicense
 
 const Version = {{ printf "%q" .Version }}
@@ -78,13 +76,11 @@ func run() error {
 	urlToLicense := buildURLToLicenseMap(result)
 
 	err = tmp.Execute(f, struct {
-		Timestamp    time.Time
 		URL          string
 		Version      string
 		LicenseIDs   map[string]string
 		URLToLicense map[string]string
 	}{
-		Timestamp:    time.Now(),
 		URL:          url,
 		Version:      result.Version,
 		LicenseIDs:   licenseIDs,

internal/task/package_tasks.go

@@ -3,6 +3,7 @@ package task
 import (
 	"github.com/anchore/syft/syft/cataloging/pkgcataloging"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/ai"
 	"github.com/anchore/syft/syft/pkg/cataloger/alpine"
 	"github.com/anchore/syft/syft/pkg/cataloger/arch"
 	"github.com/anchore/syft/syft/pkg/cataloger/binary"
@@ -52,6 +53,9 @@ const (
 	JavaScript = "javascript"
 	Node       = "node"
 	NPM        = "npm"
+
+	// Python ecosystem labels
+	Python = "python"
 )
 
 //nolint:funlen
@@ -109,7 +113,7 @@ func DefaultPackageTaskFactories() Factories {
 			func(cfg CatalogingFactoryConfig) pkg.Cataloger {
 				return python.NewPackageCataloger(cfg.PackagesConfig.Python)
 			},
-			pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "python",
+			pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, Python,
 		),
 		newSimplePackageTaskFactory(ruby.NewGemFileLockCataloger, pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "ruby", "gem"),
 		newSimplePackageTaskFactory(ruby.NewGemSpecCataloger, pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "ruby", "gem", "gemspec"),
@@ -127,7 +131,7 @@ func DefaultPackageTaskFactories() Factories {
 			pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "dotnet", "c#",
 		),
 		newSimplePackageTaskFactory(dotnet.NewDotnetPackagesLockCataloger, pkgcataloging.DeclaredTag, pkgcataloging.ImageTag, pkgcataloging.DirectoryTag, pkgcataloging.LanguageTag, "dotnet", "c#"),
-		newSimplePackageTaskFactory(python.NewInstalledPackageCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.LanguageTag, "python"),
+		newSimplePackageTaskFactory(python.NewInstalledPackageCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, pkgcataloging.LanguageTag, Python),
 		newPackageTaskFactory(
 			func(cfg CatalogingFactoryConfig) pkg.Cataloger {
 				return golang.NewGoModuleBinaryCataloger(cfg.PackagesConfig.Golang)
@@ -175,12 +179,13 @@ func DefaultPackageTaskFactories() Factories {
 		newSimplePackageTaskFactory(homebrew.NewCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, "homebrew"),
 		newSimplePackageTaskFactory(conda.NewCondaMetaCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.PackageTag, "conda"),
 		newSimplePackageTaskFactory(snap.NewCataloger, pkgcataloging.DirectoryTag, pkgcataloging.InstalledTag, pkgcataloging.ImageTag, "snap"),
+		newSimplePackageTaskFactory(ai.NewGGUFCataloger, pkgcataloging.DirectoryTag, pkgcataloging.ImageTag, "ai", "model", "gguf", "ml"),
 
 		// deprecated catalogers ////////////////////////////////////////
 		// these are catalogers that should not be selectable other than specific inclusion via name or "deprecated" tag (to remain backwards compatible)
-		newSimplePackageTaskFactory(dotnet.NewDotnetDepsCataloger, pkgcataloging.DeprecatedTag),               // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(dotnet.NewDotnetPortableExecutableCataloger, pkgcataloging.DeprecatedTag), // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(php.NewPeclCataloger, pkgcataloging.DeprecatedTag),                        // TODO: remove in syft v2.0
-		newSimplePackageTaskFactory(nix.NewStoreCataloger, pkgcataloging.DeprecatedTag),                       // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(dotnet.NewDotnetDepsCataloger, pkgcataloging.DeprecatedTag),               //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(dotnet.NewDotnetPortableExecutableCataloger, pkgcataloging.DeprecatedTag), //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(php.NewPeclCataloger, pkgcataloging.DeprecatedTag),                        //nolint:staticcheck // TODO: remove in syft v2.0
+		newSimplePackageTaskFactory(nix.NewStoreCataloger, pkgcataloging.DeprecatedTag),                       //nolint:staticcheck // TODO: remove in syft v2.0
 	}
 }

internal/task/unknowns_tasks.go

@@ -4,7 +4,8 @@ import (
 	"context"
 	"strings"
 
-	"github.com/anchore/archiver/v3"
+	"github.com/mholt/archives"
+
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/internal/sbomsync"
 	"github.com/anchore/syft/syft/cataloging"
@@ -57,9 +58,10 @@ func (c unknownsLabelerTask) finalize(resolver file.Resolver, s *sbom.SBOM) {
 	}
 
 	if c.IncludeUnexpandedArchives {
+		ctx := context.Background()
 		for coords := range s.Artifacts.FileMetadata {
-			unarchiver, notArchiveErr := archiver.ByExtension(coords.RealPath)
-			if unarchiver != nil && notArchiveErr == nil && !hasPackageReference(coords) {
+			format, _, notArchiveErr := archives.Identify(ctx, coords.RealPath, nil)
+			if format != nil && notArchiveErr == nil && !hasPackageReference(coords) {
 				s.Artifacts.Unknowns[coords] = append(s.Artifacts.Unknowns[coords], "archive not cataloged")
 			}
 		}

schema/json/schema-latest.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "anchore.io/schema/syft/json/16.0.40/document",
+  "$id": "anchore.io/schema/syft/json/16.1.0/document",
   "$ref": "#/$defs/Document",
   "$defs": {
     "AlpmDbEntry": {
@@ -130,7 +130,8 @@
           "description": "Digests contains file content hashes for integrity verification"
         }
       },
-      "type": "object"
+      "type": "object",
+      "description": "AlpmFileRecord represents a single file entry within an Arch Linux package with its associated metadata tracked by pacman."
     },
     "ApkDbEntry": {
       "properties": {
@@ -433,16 +434,19 @@
     "CPE": {
       "properties": {
         "cpe": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the CPE string identifier."
         },
         "source": {
-          "type": "string"
+          "type": "string",
+          "description": "Source is the source where this CPE was obtained or generated from."
         }
       },
       "type": "object",
       "required": [
         "cpe"
-      ]
+      ],
+      "description": "CPE represents a Common Platform Enumeration identifier used for matching packages to known vulnerabilities in security databases."
     },
     "ClassifierMatch": {
       "properties": {
@@ -747,19 +751,23 @@
     "Descriptor": {
       "properties": {
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the name of the tool that generated this SBOM (e.g., \"syft\")."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the version of the tool that generated this SBOM."
         },
-        "configuration": true
+        "configuration": {
+          "description": "Configuration contains the tool configuration used during SBOM generation."
+        }
       },
       "type": "object",
       "required": [
         "name",
         "version"
       ],
-      "description": "Descriptor describes what created the document as well as surrounding metadata"
+      "description": "Descriptor identifies the tool that generated this SBOM document, including its name, version, and configuration used during catalog generation."
     },
     "Digest": {
       "properties": {
@@ -1285,58 +1293,71 @@
     "File": {
       "properties": {
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is a unique identifier for this file within the SBOM."
         },
         "location": {
-          "$ref": "#/$defs/Coordinates"
+          "$ref": "#/$defs/Coordinates",
+          "description": "Location is the file path and layer information where this file was found."
         },
         "metadata": {
-          "$ref": "#/$defs/FileMetadataEntry"
+          "$ref": "#/$defs/FileMetadataEntry",
+          "description": "Metadata contains filesystem metadata such as permissions, ownership, and file type."
         },
         "contents": {
-          "type": "string"
+          "type": "string",
+          "description": "Contents is the file contents for small files."
         },
         "digests": {
           "items": {
             "$ref": "#/$defs/Digest"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Digests contains cryptographic hashes of the file contents."
         },
         "licenses": {
           "items": {
             "$ref": "#/$defs/FileLicense"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Licenses contains license information discovered within this file."
         },
         "executable": {
-          "$ref": "#/$defs/Executable"
+          "$ref": "#/$defs/Executable",
+          "description": "Executable contains executable metadata if this file is a binary."
         },
         "unknowns": {
           "items": {
             "type": "string"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Unknowns contains unknown fields for forward compatibility."
         }
       },
       "type": "object",
       "required": [
         "id",
         "location"
-      ]
+      ],
+      "description": "File represents a file discovered during cataloging with its metadata, content digests, licenses, and relationships to packages."
     },
     "FileLicense": {
       "properties": {
         "value": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the raw license identifier or text as found in the file."
         },
         "spdxExpression": {
-          "type": "string"
+          "type": "string",
+          "description": "SPDXExpression is the parsed SPDX license expression."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the license type classification (e.g., declared, concluded, discovered)."
         },
         "evidence": {
-          "$ref": "#/$defs/FileLicenseEvidence"
+          "$ref": "#/$defs/FileLicenseEvidence",
+          "description": "Evidence contains supporting evidence for this license detection."
         }
       },
       "type": "object",
@@ -1344,18 +1365,22 @@
         "value",
         "spdxExpression",
         "type"
-      ]
+      ],
+      "description": "FileLicense represents license information discovered within a file's contents or metadata, including the matched license text and SPDX expression."
     },
     "FileLicenseEvidence": {
       "properties": {
         "confidence": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Confidence is the confidence score for this license detection (0-100)."
         },
         "offset": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Offset is the byte offset where the license text starts in the file."
         },
         "extent": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Extent is the length of the license text in bytes."
         }
       },
       "type": "object",
@@ -1363,30 +1388,38 @@
         "confidence",
         "offset",
         "extent"
-      ]
+      ],
+      "description": "FileLicenseEvidence contains supporting evidence for a license detection in a file, including the byte offset, extent, and confidence level."
     },
     "FileMetadataEntry": {
       "properties": {
         "mode": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Mode is the Unix file permission mode in octal format."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the file type (e.g., \"RegularFile\", \"Directory\", \"SymbolicLink\")."
         },
         "linkDestination": {
-          "type": "string"
+          "type": "string",
+          "description": "LinkDestination is the target path for symbolic links."
         },
         "userID": {
-          "type": "integer"
+          "type": "integer",
+          "description": "UserID is the file owner user ID."
         },
         "groupID": {
-          "type": "integer"
+          "type": "integer",
+          "description": "GroupID is the file owner group ID."
         },
         "mimeType": {
-          "type": "string"
+          "type": "string",
+          "description": "MIMEType is the MIME type of the file contents."
         },
         "size": {
-          "type": "integer"
+          "type": "integer",
+          "description": "Size is the file size in bytes."
         }
       },
       "type": "object",
@@ -1397,7 +1430,50 @@
         "groupID",
         "mimeType",
         "size"
-      ]
+      ],
+      "description": "FileMetadataEntry contains filesystem-level metadata attributes such as permissions, ownership, type, and size for a cataloged file."
+    },
+    "GgufFileHeader": {
+      "properties": {
+        "ggufVersion": {
+          "type": "integer",
+          "description": "GGUFVersion is the GGUF format version (e.g., 3)"
+        },
+        "fileSize": {
+          "type": "integer",
+          "description": "FileSize is the size of the GGUF file in bytes (best-effort if available from resolver)"
+        },
+        "architecture": {
+          "type": "string",
+          "description": "Architecture is the model architecture (from general.architecture, e.g., \"qwen3moe\", \"llama\")"
+        },
+        "quantization": {
+          "type": "string",
+          "description": "Quantization is the quantization type (e.g., \"IQ4_NL\", \"Q4_K_M\")"
+        },
+        "parameters": {
+          "type": "integer",
+          "description": "Parameters is the number of model parameters (if present in header)"
+        },
+        "tensorCount": {
+          "type": "integer",
+          "description": "TensorCount is the number of tensors in the model"
+        },
+        "header": {
+          "type": "object",
+          "description": "RemainingKeyValues contains the remaining key-value pairs from the GGUF header that are not already\nrepresented as typed fields above. This preserves additional metadata fields for reference\n(namespaced with general.*, llama.*, etc.) while avoiding duplication."
+        },
+        "metadataHash": {
+          "type": "string",
+          "description": "MetadataKeyValuesHash is a xx64 hash of all key-value pairs from the GGUF header metadata.\nThis hash is computed over the complete header metadata (including the fields extracted\ninto typed fields above) and provides a stable identifier for the model configuration\nacross different file locations or remotes. It allows matching identical models even\nwhen stored in different repositories or with different filenames."
+        }
+      },
+      "type": "object",
+      "required": [
+        "ggufVersion",
+        "tensorCount"
+      ],
+      "description": "GGUFFileHeader represents metadata extracted from a GGUF (GPT-Generated Unified Format) model file."
     },
     "GithubActionsUseStatement": {
       "properties": {
@@ -1545,7 +1621,8 @@
       "items": {
         "type": "string"
       },
-      "type": "array"
+      "type": "array",
+      "description": "IDLikes represents a list of distribution IDs that this Linux distribution is similar to or derived from, as defined in os-release ID_LIKE field."
     },
     "JavaArchive": {
       "properties": {
@@ -1876,15 +1953,48 @@
         "integrity": {
           "type": "string",
           "description": "Integrity is Subresource Integrity hash for verification using standard SRI format (sha512-... or sha1-...). npm changed from SHA-1 to SHA-512 in newer versions. For registry sources this is the integrity from registry, for remote tarballs it's SHA-512 of the file. npm verifies tarball matches this hash before unpacking, throwing EINTEGRITY error if mismatch detected."
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their version markers, i.e. \"lodash\": \"^1.0.0\""
         }
       },
       "type": "object",
       "required": [
         "resolved",
-        "integrity"
+        "integrity",
+        "dependencies"
       ],
       "description": "NpmPackageLockEntry represents a single entry within the \"packages\" section of a package-lock.json file."
     },
+    "JavascriptPnpmLockEntry": {
+      "properties": {
+        "resolution": {
+          "$ref": "#/$defs/PnpmLockResolution",
+          "description": "Resolution is the resolution information for the package"
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their versions"
+        }
+      },
+      "type": "object",
+      "required": [
+        "resolution",
+        "dependencies"
+      ],
+      "description": "PnpmLockEntry represents a single entry in the \"packages\" section of a pnpm-lock.yaml file."
+    },
     "JavascriptYarnLockEntry": {
       "properties": {
         "resolved": {
@@ -1894,12 +2004,22 @@
         "integrity": {
           "type": "string",
           "description": "Integrity is Subresource Integrity hash for verification (SRI format)"
+        },
+        "dependencies": {
+          "patternProperties": {
+            ".*": {
+              "type": "string"
+            }
+          },
+          "type": "object",
+          "description": "Dependencies is a map of dependencies and their versions"
         }
       },
       "type": "object",
       "required": [
         "resolved",
-        "integrity"
+        "integrity",
+        "dependencies"
       ],
       "description": "YarnLockEntry represents a single entry section of a yarn.lock file."
     },
@@ -1931,28 +2051,34 @@
     "License": {
       "properties": {
         "value": {
-          "type": "string"
+          "type": "string",
+          "description": "Value is the raw license identifier or expression as found."
         },
         "spdxExpression": {
-          "type": "string"
+          "type": "string",
+          "description": "SPDXExpression is the parsed SPDX license expression."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the license type classification (e.g., declared, concluded, discovered)."
         },
         "urls": {
           "items": {
             "type": "string"
           },
-          "type": "array"
+          "type": "array",
+          "description": "URLs are URLs where license text or information can be found."
         },
         "locations": {
           "items": {
             "$ref": "#/$defs/Location"
           },
-          "type": "array"
+          "type": "array",
+          "description": "Locations are file locations where this license was discovered."
         },
         "contents": {
-          "type": "string"
+          "type": "string",
+          "description": "Contents is the full license text content."
         }
       },
       "type": "object",
@@ -1962,7 +2088,8 @@
         "type",
         "urls",
         "locations"
-      ]
+      ],
+      "description": "License represents software license information discovered for a package, including SPDX expressions and supporting evidence locations."
     },
     "LinuxKernelArchive": {
       "properties": {
@@ -2087,64 +2214,84 @@
     "LinuxRelease": {
       "properties": {
         "prettyName": {
-          "type": "string"
+          "type": "string",
+          "description": "PrettyName is a human-readable operating system name with version."
         },
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the operating system name without version information."
         },
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is the lower-case operating system identifier (e.g., \"ubuntu\", \"rhel\")."
         },
         "idLike": {
-          "$ref": "#/$defs/IDLikes"
+          "$ref": "#/$defs/IDLikes",
+          "description": "IDLike is a list of operating system IDs this distribution is similar to or derived from."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the operating system version including codename if available."
         },
         "versionID": {
-          "type": "string"
+          "type": "string",
+          "description": "VersionID is the operating system version number or identifier."
         },
         "versionCodename": {
-          "type": "string"
+          "type": "string",
+          "description": "VersionCodename is the operating system release codename (e.g., \"jammy\", \"bullseye\")."
         },
         "buildID": {
-          "type": "string"
+          "type": "string",
+          "description": "BuildID is a build identifier for the operating system."
         },
         "imageID": {
-          "type": "string"
+          "type": "string",
+          "description": "ImageID is an identifier for container or cloud images."
         },
         "imageVersion": {
-          "type": "string"
+          "type": "string",
+          "description": "ImageVersion is the version for container or cloud images."
         },
         "variant": {
-          "type": "string"
+          "type": "string",
+          "description": "Variant is the operating system variant name (e.g., \"Server\", \"Workstation\")."
         },
         "variantID": {
-          "type": "string"
+          "type": "string",
+          "description": "VariantID is the lower-case operating system variant identifier."
         },
         "homeURL": {
-          "type": "string"
+          "type": "string",
+          "description": "HomeURL is the homepage URL for the operating system."
         },
         "supportURL": {
-          "type": "string"
+          "type": "string",
+          "description": "SupportURL is the support or help URL for the operating system."
         },
         "bugReportURL": {
-          "type": "string"
+          "type": "string",
+          "description": "BugReportURL is the bug reporting URL for the operating system."
         },
         "privacyPolicyURL": {
-          "type": "string"
+          "type": "string",
+          "description": "PrivacyPolicyURL is the privacy policy URL for the operating system."
         },
         "cpeName": {
-          "type": "string"
+          "type": "string",
+          "description": "CPEName is the Common Platform Enumeration name for the operating system."
         },
         "supportEnd": {
-          "type": "string"
+          "type": "string",
+          "description": "SupportEnd is the end of support date or version identifier."
         },
         "extendedSupport": {
-          "type": "boolean"
+          "type": "boolean",
+          "description": "ExtendedSupport indicates whether extended security or support is available."
         }
       },
-      "type": "object"
+      "type": "object",
+      "description": "LinuxRelease contains Linux distribution identification and version information extracted from /etc/os-release or similar system files."
     },
     "Location": {
       "properties": {
@@ -2240,7 +2387,7 @@
         "product_id",
         "kb"
       ],
-      "description": "MicrosoftKbPatch is slightly odd in how it is expected to map onto data."
+      "description": "MicrosoftKbPatch represents a Windows Knowledge Base patch identifier associated with a specific Microsoft product from the MSRC (Microsoft Security Response Center)."
     },
     "NixDerivation": {
       "properties": {
@@ -2474,6 +2621,9 @@
             {
               "$ref": "#/$defs/ErlangRebarLockEntry"
             },
+            {
+              "$ref": "#/$defs/GgufFileHeader"
+            },
             {
               "$ref": "#/$defs/GithubActionsUseStatement"
             },
@@ -2507,6 +2657,9 @@
             {
               "$ref": "#/$defs/JavascriptNpmPackageLockEntry"
             },
+            {
+              "$ref": "#/$defs/JavascriptPnpmLockEntry"
+            },
             {
               "$ref": "#/$defs/JavascriptYarnLockEntry"
             },
@@ -2549,6 +2702,9 @@
             {
               "$ref": "#/$defs/PythonPackage"
             },
+            {
+              "$ref": "#/$defs/PythonPdmLockEntry"
+            },
             {
               "$ref": "#/$defs/PythonPipRequirementsEntry"
             },
@@ -2955,6 +3111,19 @@
       ],
       "description": "PhpPeclEntry represents a single package entry found within php pecl metadata files."
     },
+    "PnpmLockResolution": {
+      "properties": {
+        "integrity": {
+          "type": "string",
+          "description": "Integrity is Subresource Integrity hash for verification (SRI format)"
+        }
+      },
+      "type": "object",
+      "required": [
+        "integrity"
+      ],
+      "description": "PnpmLockResolution contains package resolution metadata from pnpm lockfiles, including the integrity hash used for verification."
+    },
     "PortageDbEntry": {
       "properties": {
         "installedSize": {
@@ -3131,6 +3300,100 @@
       ],
       "description": "PythonPackage represents all captured data for a python egg or wheel package (specifically as outlined in the PyPA core metadata specification https://packaging.python.org/en/latest/specifications/core-metadata/)."
     },
+    "PythonPdmFileEntry": {
+      "properties": {
+        "url": {
+          "type": "string",
+          "description": "URL is the file download URL"
+        },
+        "digest": {
+          "$ref": "#/$defs/PythonFileDigest",
+          "description": "Digest is the hash digest of the file hosted at the URL"
+        }
+      },
+      "type": "object",
+      "required": [
+        "url",
+        "digest"
+      ]
+    },
+    "PythonPdmLockEntry": {
+      "properties": {
+        "summary": {
+          "type": "string",
+          "description": "Summary provides a description of the package"
+        },
+        "files": {
+          "items": {
+            "$ref": "#/$defs/PythonPdmFileEntry"
+          },
+          "type": "array",
+          "description": "Files are the package files with their paths and hash digests (for the base package without extras)"
+        },
+        "marker": {
+          "type": "string",
+          "description": "Marker is the \"environment\" --conditional expressions that determine whether a package should be installed based on the runtime environment"
+        },
+        "requiresPython": {
+          "type": "string",
+          "description": "RequiresPython specifies the Python version requirement (e.g., \"\u003e=3.6\")."
+        },
+        "dependencies": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array",
+          "description": "Dependencies are the dependency specifications for the base package (without extras)"
+        },
+        "extras": {
+          "items": {
+            "$ref": "#/$defs/PythonPdmLockExtraVariant"
+          },
+          "type": "array",
+          "description": "Extras contains variants for different extras combinations (PDM may have multiple entries per package)"
+        }
+      },
+      "type": "object",
+      "required": [
+        "summary",
+        "files"
+      ],
+      "description": "PythonPdmLockEntry represents a single package entry within a pdm.lock file."
+    },
+    "PythonPdmLockExtraVariant": {
+      "properties": {
+        "extras": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array",
+          "description": "Extras are the optional extras enabled for this variant (e.g., [\"toml\"], [\"dev\"], or [\"toml\", \"dev\"])"
+        },
+        "dependencies": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array",
+          "description": "Dependencies are the dependencies specific to this extras variant"
+        },
+        "files": {
+          "items": {
+            "$ref": "#/$defs/PythonPdmFileEntry"
+          },
+          "type": "array",
+          "description": "Files are the package files specific to this variant (only populated if different from base)"
+        },
+        "marker": {
+          "type": "string",
+          "description": "Marker is the environment conditional expression for this variant (e.g., \"python_version \u003c \\\"3.11\\\"\")"
+        }
+      },
+      "type": "object",
+      "required": [
+        "extras"
+      ],
+      "description": "PythonPdmLockExtraVariant represents a specific extras combination variant within a PDM lock file."
+    },
     "PythonPipRequirementsEntry": {
       "properties": {
         "name": {
@@ -3411,22 +3674,28 @@
     "Relationship": {
       "properties": {
         "parent": {
-          "type": "string"
+          "type": "string",
+          "description": "Parent is the ID of the parent artifact in this relationship."
         },
         "child": {
-          "type": "string"
+          "type": "string",
+          "description": "Child is the ID of the child artifact in this relationship."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the relationship type (e.g., \"contains\", \"dependency-of\", \"ancestor-of\")."
         },
-        "metadata": true
+        "metadata": {
+          "description": "Metadata contains additional relationship-specific metadata."
+        }
       },
       "type": "object",
       "required": [
         "parent",
         "child",
         "type"
-      ]
+      ],
+      "description": "Relationship represents a directed relationship between two artifacts in the SBOM, such as package-contains-file or package-depends-on-package."
     },
     "RpmArchive": {
       "properties": {
@@ -3773,17 +4042,20 @@
     "Schema": {
       "properties": {
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the JSON schema version for this document format."
         },
         "url": {
-          "type": "string"
+          "type": "string",
+          "description": "URL is the URL to the JSON schema definition document."
         }
       },
       "type": "object",
       "required": [
         "version",
         "url"
-      ]
+      ],
+      "description": "Schema specifies the JSON schema version and URL reference that defines the structure and validation rules for this document format."
     },
     "SnapEntry": {
       "properties": {
@@ -3821,21 +4093,28 @@
     "Source": {
       "properties": {
         "id": {
-          "type": "string"
+          "type": "string",
+          "description": "ID is a unique identifier for the analyzed source artifact."
         },
         "name": {
-          "type": "string"
+          "type": "string",
+          "description": "Name is the name of the analyzed artifact (e.g., image name, directory path)."
         },
         "version": {
-          "type": "string"
+          "type": "string",
+          "description": "Version is the version of the analyzed artifact (e.g., image tag)."
         },
         "supplier": {
-          "type": "string"
+          "type": "string",
+          "description": "Supplier is supplier information, which can be user-provided for NTIA minimum elements compliance."
         },
         "type": {
-          "type": "string"
+          "type": "string",
+          "description": "Type is the source type (e.g., \"image\", \"directory\", \"file\")."
         },
-        "metadata": true
+        "metadata": {
+          "description": "Metadata contains additional source-specific metadata."
+        }
       },
       "type": "object",
       "required": [
@@ -3845,7 +4124,7 @@
         "type",
         "metadata"
       ],
-      "description": "Instead, the Supplier can be determined by the user of syft and passed as a config or flag to help fulfill the NTIA minimum elements."
+      "description": "Source represents the artifact that was analyzed to generate this SBOM, such as a container image, directory, or file archive."
     },
     "SwiftPackageManagerLockEntry": {
       "properties": {

syft/file/cataloger/executable/macho.go

@@ -3,6 +3,7 @@ package executable
 import (
 	"debug/macho"
 
+	"github.com/anchore/syft/internal"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/internal/unionreader"
 )
@@ -19,20 +20,38 @@ const (
 func findMachoFeatures(data *file.Executable, reader unionreader.UnionReader) error {
 	// TODO: support security features
 
-	// TODO: support multi-architecture binaries
-	f, err := macho.NewFile(reader)
+	// a universal binary may have multiple architectures, so we need to check each one
+	readers, err := unionreader.GetReaders(reader)
 	if err != nil {
 		return err
 	}
 
-	libs, err := f.ImportedLibraries()
-	if err != nil {
-		return err
+	var libs []string
+	for _, r := range readers {
+		f, err := macho.NewFile(r)
+		if err != nil {
+			return err
+		}
+
+		rLibs, err := f.ImportedLibraries()
+		if err != nil {
+			return err
+		}
+		libs = append(libs, rLibs...)
+
+		// TODO handle only some having entrypoints/exports? If that is even practical
+		// only check for entrypoint if we don't already have one
+		if !data.HasEntrypoint {
+			data.HasEntrypoint = machoHasEntrypoint(f)
+		}
+		// only check for exports if we don't already have them
+		if !data.HasExports {
+			data.HasExports = machoHasExports(f)
+		}
 	}
 
-	data.ImportedLibraries = libs
-	data.HasEntrypoint = machoHasEntrypoint(f)
-	data.HasExports = machoHasExports(f)
+	// de-duplicate libraries
+	data.ImportedLibraries = internal.NewSet(libs...).ToSlice()
 
 	return nil
 }

syft/file/cataloger/executable/macho_test.go

@@ -9,6 +9,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/internal/unionreader"
 )
 
@@ -83,3 +84,39 @@ func Test_machoHasExports(t *testing.T) {
 		})
 	}
 }
+
+func Test_machoUniversal(t *testing.T) {
+	readerForFixture := func(t *testing.T, fixture string) unionreader.UnionReader {
+		t.Helper()
+		f, err := os.Open(filepath.Join("test-fixtures/shared-info", fixture))
+		require.NoError(t, err)
+		return f
+	}
+
+	tests := []struct {
+		name    string
+		fixture string
+		want    file.Executable
+	}{
+		{
+			name:    "universal lib",
+			fixture: "bin/libhello_universal.dylib",
+			want:    file.Executable{HasExports: true, HasEntrypoint: false},
+		},
+		{
+			name:    "universal application",
+			fixture: "bin/hello_mac_universal",
+			want:    file.Executable{HasExports: false, HasEntrypoint: true},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var data file.Executable
+			err := findMachoFeatures(&data, readerForFixture(t, tt.fixture))
+			require.NoError(t, err)
+
+			assert.Equal(t, tt.want.HasEntrypoint, data.HasEntrypoint)
+			assert.Equal(t, tt.want.HasExports, data.HasExports)
+		})
+	}
+}

syft/file/cataloger/executable/test-fixtures/shared-info/project/hello/Makefile

@@ -2,13 +2,13 @@
 
 BIN=../../bin
 
-all: $(BIN)/hello_linux $(BIN)/hello.exe $(BIN)/hello_mac
+all: $(BIN)/hello_linux $(BIN)/hello.exe $(BIN)/hello_mac $(BIN)/hello_mac_universal
 
 linux: $(BIN)/libhello.so
 
 windows: $(BIN)/libhello.dll
 
-mac: $(BIN)/libhello.dylib
+mac: $(BIN)/libhello.dylib $(BIN)/hello_mac_universal
 
 $(BIN)/hello_linux:
 	gcc hello.c -o $(BIN)/hello_linux
@@ -19,5 +19,8 @@ $(BIN)/hello.exe:
 $(BIN)/hello_mac:
 	o64-clang hello.c -o $(BIN)/hello_mac
 
+$(BIN)/hello_mac_universal:
+	o64-clang -arch arm64 -arch x86_64 hello.c -o $(BIN)/hello_mac_universal
+
 clean:
-	rm -f $(BIN)/hello_linux $(BIN)/hello.exe $(BIN)/hello_mac
+	rm -f $(BIN)/hello_linux $(BIN)/hello.exe $(BIN)/hello_mac $(BIN)/hello_mac_universal

syft/file/cataloger/executable/test-fixtures/shared-info/project/libhello/Makefile

@@ -2,13 +2,13 @@
 
 BIN=../../bin
 
-all:  $(BIN)/libhello.so  $(BIN)/libhello.dll $(BIN)/libhello.dylib
+all:  $(BIN)/libhello.so  $(BIN)/libhello.dll $(BIN)/libhello.dylib $(BIN)/libhello_universal.dylib
 
 linux: $(BIN)/libhello.so
 
 windows: $(BIN)/libhello.dll
 
-mac: $(BIN)/libhello.dylib
+mac: $(BIN)/libhello.dylib $(BIN)/libhello_universal.dylib
 
 $(BIN)/libhello.so:
 	gcc -shared -fPIC -o $(BIN)/libhello.so hello.c
@@ -19,5 +19,8 @@ $(BIN)/libhello.dll:
 $(BIN)/libhello.dylib:
 	o64-clang -dynamiclib -o $(BIN)/libhello.dylib hello.c
 
+$(BIN)/libhello_universal.dylib:
+	o64-clang -dynamiclib -arch arm64 -arch x86_64 hello.c -o $(BIN)/libhello_universal.dylib
+
 clean:
-	rm -f $(BIN)/libhello.so $(BIN)/hello.dll $(BIN)/libhello.dylib $(BIN)/libhello.a
+	rm -f $(BIN)/libhello.so $(BIN)/hello.dll $(BIN)/libhello.dylib $(BIN)/libhello.a $(BIN)/libhello_universal.dylib

syft/format/cpes/decoder.go

@@ -0,0 +1,95 @@
+package cpes
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"io"
+	"strings"
+
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/syft/cpe"
+	"github.com/anchore/syft/syft/format/internal"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+const ID sbom.FormatID = "cpes"
+const version = "1"
+
+var _ sbom.FormatDecoder = (*decoder)(nil)
+
+type decoder struct{}
+
+func NewFormatDecoder() sbom.FormatDecoder {
+	return decoder{}
+}
+
+func (d decoder) Decode(r io.Reader) (*sbom.SBOM, sbom.FormatID, string, error) {
+	if r == nil {
+		return nil, "", "", fmt.Errorf("no reader provided")
+	}
+	s, err := toSyftModel(r)
+	return s, ID, version, err
+}
+
+func (d decoder) Identify(r io.Reader) (sbom.FormatID, string) {
+	if r == nil {
+		return "", ""
+	}
+
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if line == "" {
+			// skip whitespace only lines
+			continue
+		}
+
+		err := cpe.ValidateString(line)
+		if err != nil {
+			return "", ""
+		}
+
+		return ID, version
+	}
+
+	return "", ""
+}
+
+func toSyftModel(r io.Reader) (*sbom.SBOM, error) {
+	var errs []error
+	pkgs := pkg.NewCollection()
+
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+
+		if line == "" {
+			continue
+		}
+
+		// skip invalid CPEs
+		c, err := cpe.New(line, "")
+		if err != nil {
+			log.WithFields("error", err, "line", line).Debug("unable to parse cpe")
+			continue
+		}
+
+		p := pkg.Package{
+			Name:    c.Attributes.Product,
+			Version: c.Attributes.Version,
+			CPEs:    []cpe.CPE{c},
+		}
+
+		internal.Backfill(&p)
+		p.SetID()
+		pkgs.Add(p)
+	}
+
+	return &sbom.SBOM{
+		Artifacts: sbom.Artifacts{
+			Packages: pkgs,
+		},
+	}, errors.Join(errs...)
+}

syft/format/cpes/decoder_test.go

@@ -0,0 +1,171 @@
+package cpes
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/google/go-cmp/cmp"
+	"github.com/google/go-cmp/cmp/cmpopts"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/syft/cpe"
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/sbom"
+)
+
+func Test_CPEProvider(t *testing.T) {
+	tests := []struct {
+		name      string
+		userInput string
+		sbom      *sbom.SBOM
+	}{
+		{
+			name:      "takes a single cpe",
+			userInput: "cpe:/a:apache:log4j:2.14.1",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name:    "log4j",
+						Version: "2.14.1",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:/a:apache:log4j:2.14.1", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name: "takes multiple cpes",
+			userInput: `cpe:/a:apache:log4j:2.14.1
+						cpe:2.3:a:f5:nginx:*:*:*:*:*:*:*:*;
+						cpe:2.3:a:f5:nginx:0.5.2:*:*:*:*:*:*:*;
+						cpe:2.3:a:f5:nginx:0.5.3:*:*:*:*:*:*:*;`,
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(
+						pkg.Package{
+							Name:    "log4j",
+							Version: "2.14.1",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:/a:apache:log4j:2.14.1", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:*:*:*:*:*:*:*:*;", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "0.5.2",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:0.5.2:*:*:*:*:*:*:*;", ""),
+							},
+						},
+						pkg.Package{
+							Name:    "nginx",
+							Version: "0.5.3",
+							CPEs: []cpe.CPE{
+								cpe.Must("cpe:2.3:a:f5:nginx:0.5.3:*:*:*:*:*:*:*;", ""),
+							},
+						},
+					),
+				},
+			},
+		},
+		{
+			name:      "takes cpe with no version",
+			userInput: "cpe:/a:apache:log4j",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "log4j",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:/a:apache:log4j", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "takes CPE 2.3 format",
+			userInput: "cpe:2.3:a:apache:log4j:2.14.1:*:*:*:*:*:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name:    "log4j",
+						Version: "2.14.1",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:apache:log4j:2.14.1:*:*:*:*:*:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "deduces target SW from CPE - known target_sw",
+			userInput: "cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "opensearch",
+						Type: pkg.GemPkg,
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "handles unknown target_sw CPE field",
+			userInput: "cpe:2.3:a:amazon:opensearch:*:*:*:*:*:loremipsum:*:*",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(pkg.Package{
+						Name: "opensearch",
+						Type: "",
+						CPEs: []cpe.CPE{
+							cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:loremipsum:*:*", ""),
+						},
+					}),
+				},
+			},
+		},
+		{
+			name:      "invalid prefix",
+			userInput: "dir:test-fixtures/cpe",
+			sbom: &sbom.SBOM{
+				Artifacts: sbom.Artifacts{
+					Packages: pkg.NewCollection(),
+				},
+			},
+		},
+	}
+
+	syftPkgOpts := []cmp.Option{
+		cmpopts.IgnoreFields(pkg.Package{}, "id", "Language"),
+		cmpopts.IgnoreUnexported(pkg.Package{}, file.LocationSet{}, pkg.LicenseSet{}),
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			dec := NewFormatDecoder()
+
+			decodedSBOM, _, _, err := dec.Decode(strings.NewReader(tc.userInput))
+			require.NoError(t, err)
+
+			gotSyftPkgs := decodedSBOM.Artifacts.Packages.Sorted()
+			wantSyftPkgs := tc.sbom.Artifacts.Packages.Sorted()
+			require.Equal(t, len(gotSyftPkgs), len(wantSyftPkgs))
+			for idx, wantPkg := range wantSyftPkgs {
+				if d := cmp.Diff(wantPkg, gotSyftPkgs[idx], syftPkgOpts...); d != "" {
+					t.Errorf("unexpected Syft Package (-want +got):\n%s", d)
+				}
+			}
+		})
+	}
+}

syft/format/decoders.go

@@ -3,6 +3,7 @@ package format
 import (
 	"io"
 
+	"github.com/anchore/syft/syft/format/cpes"
 	"github.com/anchore/syft/syft/format/cyclonedxjson"
 	"github.com/anchore/syft/syft/format/cyclonedxxml"
 	"github.com/anchore/syft/syft/format/purls"
@@ -26,6 +27,7 @@ func Decoders() []sbom.FormatDecoder {
 		spdxtagvalue.NewFormatDecoder(),
 		spdxjson.NewFormatDecoder(),
 		purls.NewFormatDecoder(),
+		cpes.NewFormatDecoder(),
 	}
 }
 

syft/format/github/internal/model/model.go

@@ -1,11 +1,13 @@
 package model
 
 import (
+	"context"
 	"fmt"
 	"strings"
 	"time"
 
-	"github.com/anchore/archiver/v3"
+	"github.com/mholt/archives"
+
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/pkg"
@@ -87,6 +89,9 @@ func toGithubManifests(s *sbom.SBOM) Manifests {
 		}
 
 		name := dependencyName(p)
+		if name == "" || p.PURL == "" {
+			continue
+		}
 		manifest.Resolved[name] = DependencyNode{
 			PackageURL:   p.PURL,
 			Metadata:     toDependencyMetadata(p),
@@ -150,8 +155,8 @@ func trimRelative(s string) string {
 
 // isArchive returns true if the path appears to be an archive
 func isArchive(path string) bool {
-	_, err := archiver.ByExtension(path)
-	return err == nil
+	format, _, err := archives.Identify(context.Background(), path, nil)
+	return err == nil && format != nil
 }
 
 func toDependencies(s *sbom.SBOM, p pkg.Package) (out []string) {

syft/format/github/test-fixtures/snapshot/TestGithubDirectoryEncoder.golden

@@ -16,11 +16,6 @@
         "source_location": "redacted/some/path/some/path/pkg1"
       },
       "resolved": {
-        "": {
-          "package_url": "a-purl-2",
-          "relationship": "direct",
-          "scope": "runtime"
-        },
         "pkg:deb/debian/package-2@2.0.1": {
           "package_url": "pkg:deb/debian/package-2@2.0.1",
           "relationship": "direct",

syft/format/github/test-fixtures/snapshot/TestGithubImageEncoder.golden

@@ -17,13 +17,6 @@
       },
       "metadata": {
         "syft:filesystem":"redacted"
-      },
-      "resolved": {
-        "": {
-          "package_url": "a-purl-1",
-          "relationship": "direct",
-          "scope": "runtime"
-        }
       }
     },
     "user-image-input:/somefile-2.txt": {

syft/format/internal/backfill.go

@@ -10,13 +10,31 @@ import (
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/syft/cpe"
 	"github.com/anchore/syft/syft/pkg"
+	cataloger "github.com/anchore/syft/syft/pkg/cataloger/common/cpe"
 )
 
 // Backfill takes all information present in the package and attempts to fill in any missing information
-// from any available sources, such as the Metadata and PURL.
+// from any available sources, such as the Metadata, PURL, or CPEs.
 //
 // Backfill does not call p.SetID(), but this needs to be called later to ensure it's up to date
 func Backfill(p *pkg.Package) {
+	backfillFromPurl(p)
+	backfillFromCPE(p)
+}
+
+func backfillFromCPE(p *pkg.Package) {
+	if len(p.CPEs) == 0 {
+		return
+	}
+
+	c := p.CPEs[0]
+
+	if p.Type == "" {
+		p.Type = cataloger.TargetSoftwareToPackageType(c.Attributes.TargetSW)
+	}
+}
+
+func backfillFromPurl(p *pkg.Package) {
 	if p.PURL == "" {
 		return
 	}
@@ -29,6 +47,7 @@ func Backfill(p *pkg.Package) {
 
 	var cpes []cpe.CPE
 	epoch := ""
+	rpmmod := ""
 
 	for _, qualifier := range purl.Qualifiers {
 		switch qualifier.Key {
@@ -44,6 +63,8 @@ func Backfill(p *pkg.Package) {
 			}
 		case pkg.PURLQualifierEpoch:
 			epoch = qualifier.Value
+		case pkg.PURLQualifierRpmModularity:
+			rpmmod = qualifier.Value
 		}
 	}
 
@@ -63,6 +84,10 @@ func Backfill(p *pkg.Package) {
 		setJavaMetadataFromPurl(p, purl)
 	}
 
+	if p.Type == pkg.RpmPkg {
+		setRpmMetadataFromPurl(p, rpmmod)
+	}
+
 	for _, c := range cpes {
 		if slices.Contains(p.CPEs, c) {
 			continue
@@ -82,6 +107,35 @@ func setJavaMetadataFromPurl(p *pkg.Package, _ packageurl.PackageURL) {
 	}
 }
 
+func setRpmMetadataFromPurl(p *pkg.Package, rpmmod string) {
+	if p.Type != pkg.RpmPkg {
+		return
+	}
+	if rpmmod == "" {
+		return
+	}
+
+	if p.Metadata == nil {
+		p.Metadata = pkg.RpmDBEntry{
+			ModularityLabel: &rpmmod,
+		}
+		return
+	}
+
+	switch m := p.Metadata.(type) {
+	case pkg.RpmDBEntry:
+		if m.ModularityLabel == nil {
+			m.ModularityLabel = &rpmmod
+			p.Metadata = m
+		}
+	case pkg.RpmArchive:
+		if m.ModularityLabel == nil {
+			m.ModularityLabel = &rpmmod
+			p.Metadata = m
+		}
+	}
+}
+
 func setVersionFromPurl(p *pkg.Package, purl packageurl.PackageURL, epoch string) {
 	if p.Version == "" {
 		p.Version = purl.Version

syft/format/internal/backfill_test.go

@@ -53,6 +53,21 @@ func Test_Backfill(t *testing.T) {
 				Version: "1:1.12.8-26.el8",
 			},
 		},
+		{
+			name: "rpm with rpmmod",
+			in: pkg.Package{
+				PURL: "pkg:rpm/redhat/httpd@2.4.37-51?arch=x86_64&distro=rhel-8.7&rpmmod=httpd:2.4",
+			},
+			expected: pkg.Package{
+				PURL:    "pkg:rpm/redhat/httpd@2.4.37-51?arch=x86_64&distro=rhel-8.7&rpmmod=httpd:2.4",
+				Type:    pkg.RpmPkg,
+				Name:    "httpd",
+				Version: "2.4.37-51",
+				Metadata: pkg.RpmDBEntry{
+					ModularityLabel: strRef("httpd:2.4"),
+				},
+			},
+		},
 		{
 			name: "bad cpe",
 			in: pkg.Package{
@@ -106,6 +121,20 @@ func Test_Backfill(t *testing.T) {
 				Metadata: pkg.JavaArchive{},
 			},
 		},
+		{
+			name: "target-sw from CPE",
+			in: pkg.Package{
+				CPEs: []cpe.CPE{
+					cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+				},
+			},
+			expected: pkg.Package{
+				CPEs: []cpe.CPE{
+					cpe.Must("cpe:2.3:a:amazon:opensearch:*:*:*:*:*:ruby:*:*", ""),
+				},
+				Type: pkg.GemPkg,
+			},
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -171,3 +200,7 @@ func Test_nameFromPurl(t *testing.T) {
 		})
 	}
 }
+
+func strRef(s string) *string {
+	return &s
+}

syft/format/internal/cyclonedxutil/helpers/component.go

@@ -40,8 +40,11 @@ func EncodeComponent(p pkg.Package, supplier string, locationSorter func(a, b fi
 	}
 
 	componentType := cyclonedx.ComponentTypeLibrary
-	if p.Type == pkg.BinaryPkg {
+	switch p.Type {
+	case pkg.BinaryPkg:
 		componentType = cyclonedx.ComponentTypeApplication
+	case pkg.ModelPkg:
+		componentType = cyclonedx.ComponentTypeMachineLearningModel
 	}
 
 	return cyclonedx.Component{

syft/format/internal/cyclonedxutil/helpers/decoder.go

@@ -62,7 +62,7 @@ func collectPackages(component *cyclonedx.Component, s *sbom.SBOM, idMap map[str
 	switch component.Type {
 	case cyclonedx.ComponentTypeOS:
 	case cyclonedx.ComponentTypeContainer:
-	case cyclonedx.ComponentTypeApplication, cyclonedx.ComponentTypeFramework, cyclonedx.ComponentTypeLibrary:
+	case cyclonedx.ComponentTypeApplication, cyclonedx.ComponentTypeFramework, cyclonedx.ComponentTypeLibrary, cyclonedx.ComponentTypeMachineLearningModel:
 		p := decodeComponent(component)
 		idMap[component.BOMRef] = p
 		if component.BOMRef != "" {

syft/format/internal/spdxutil/helpers/originator_supplier_test.go

@@ -40,8 +40,10 @@ func Test_OriginatorSupplier(t *testing.T) {
 		pkg.PhpComposerInstalledEntry{},
 		pkg.PhpPearEntry{},
 		pkg.PhpPeclEntry{},
+		pkg.PnpmLockEntry{},
 		pkg.PortageEntry{},
 		pkg.PythonPipfileLockEntry{},
+		pkg.PythonPdmLockEntry{},
 		pkg.PythonRequirementsEntry{},
 		pkg.PythonPoetryLockEntry{},
 		pkg.PythonUvLockEntry{},
@@ -53,6 +55,7 @@ func Test_OriginatorSupplier(t *testing.T) {
 		pkg.OpamPackage{},
 		pkg.YarnLockEntry{},
 		pkg.TerraformLockProviderEntry{},
+		pkg.GGUFFileHeader{},
 	)
 	tests := []struct {
 		name       string
@@ -342,6 +345,25 @@ func Test_OriginatorSupplier(t *testing.T) {
 			originator: "Person: auth (auth@auth.gov)",
 			supplier:   "Person: auth (auth@auth.gov)",
 		},
+		{
+			name: "from python PDM lock",
+			input: pkg.Package{
+				Metadata: pkg.PythonPdmLockEntry{
+					Files: []pkg.PythonPdmFileEntry{
+						{
+							URL: "https://pypi.org/project/testpkg/1.2.3/file1.tar.gz",
+							Digest: pkg.PythonFileDigest{
+								Algorithm: "sha256",
+								Value:     "3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651",
+							},
+						},
+					},
+					Summary: "A test package",
+				},
+			},
+			originator: "",
+			supplier:   "",
+		},
 		{
 			name: "from r -- maintainer > author",
 			input: pkg.Package{

syft/format/internal/spdxutil/helpers/source_info.go

@@ -82,6 +82,8 @@ func SourceInfo(p pkg.Package) string {
 		answer = "acquired package info from Homebrew formula"
 	case pkg.TerraformPkg:
 		answer = "acquired package info from Terraform dependency lock file"
+	case pkg.ModelPkg:
+		answer = "acquired package info from AI artifact (e.g. GGUF File"
 	default:
 		answer = "acquired package info from the following paths"
 	}

syft/format/internal/spdxutil/helpers/source_info_test.go

@@ -351,6 +351,14 @@ func Test_SourceInfo(t *testing.T) {
 				"acquired package info from Terraform dependency lock file",
 			},
 		},
+		{
+			input: pkg.Package{
+				Type: pkg.ModelPkg,
+			},
+			expected: []string{
+				"",
+			},
+		},
 	}
 	var pkgTypes []pkg.Type
 	for _, test := range tests {

syft/format/syftjson/model/document.go

@@ -35,14 +35,23 @@ func (d *Document) UnmarshalJSON(data []byte) error {
 	return nil
 }
 
-// Descriptor describes what created the document as well as surrounding metadata
+// Descriptor identifies the tool that generated this SBOM document, including its name, version, and configuration used during catalog generation.
 type Descriptor struct {
-	Name          string      `json:"name"`
-	Version       string      `json:"version"`
+	// Name is the name of the tool that generated this SBOM (e.g., "syft").
+	Name string `json:"name"`
+
+	// Version is the version of the tool that generated this SBOM.
+	Version string `json:"version"`
+
+	// Configuration contains the tool configuration used during SBOM generation.
 	Configuration interface{} `json:"configuration,omitempty"`
 }
 
+// Schema specifies the JSON schema version and URL reference that defines the structure and validation rules for this document format.
 type Schema struct {
+	// Version is the JSON schema version for this document format.
 	Version string `json:"version"`
-	URL     string `json:"url"`
+
+	// URL is the URL to the JSON schema definition document.
+	URL string `json:"url"`
 }

syft/format/syftjson/model/file.go

@@ -10,25 +10,55 @@ import (
 	"github.com/anchore/syft/syft/license"
 )
 
+// File represents a file discovered during cataloging with its metadata, content digests, licenses, and relationships to packages.
 type File struct {
-	ID         string             `json:"id"`
-	Location   file.Coordinates   `json:"location"`
-	Metadata   *FileMetadataEntry `json:"metadata,omitempty"`
-	Contents   string             `json:"contents,omitempty"`
-	Digests    []file.Digest      `json:"digests,omitempty"`
-	Licenses   []FileLicense      `json:"licenses,omitempty"`
-	Executable *file.Executable   `json:"executable,omitempty"`
-	Unknowns   []string           `json:"unknowns,omitempty"`
+	// ID is a unique identifier for this file within the SBOM.
+	ID string `json:"id"`
+
+	// Location is the file path and layer information where this file was found.
+	Location file.Coordinates `json:"location"`
+
+	// Metadata contains filesystem metadata such as permissions, ownership, and file type.
+	Metadata *FileMetadataEntry `json:"metadata,omitempty"`
+
+	// Contents is the file contents for small files.
+	Contents string `json:"contents,omitempty"`
+
+	// Digests contains cryptographic hashes of the file contents.
+	Digests []file.Digest `json:"digests,omitempty"`
+
+	// Licenses contains license information discovered within this file.
+	Licenses []FileLicense `json:"licenses,omitempty"`
+
+	// Executable contains executable metadata if this file is a binary.
+	Executable *file.Executable `json:"executable,omitempty"`
+
+	// Unknowns contains unknown fields for forward compatibility.
+	Unknowns []string `json:"unknowns,omitempty"`
 }
 
+// FileMetadataEntry contains filesystem-level metadata attributes such as permissions, ownership, type, and size for a cataloged file.
 type FileMetadataEntry struct {
-	Mode            int    `json:"mode"`
-	Type            string `json:"type"`
+	// Mode is the Unix file permission mode in octal format.
+	Mode int `json:"mode"`
+
+	// Type is the file type (e.g., "RegularFile", "Directory", "SymbolicLink").
+	Type string `json:"type"`
+
+	// LinkDestination is the target path for symbolic links.
 	LinkDestination string `json:"linkDestination,omitempty"`
-	UserID          int    `json:"userID"`
-	GroupID         int    `json:"groupID"`
-	MIMEType        string `json:"mimeType"`
-	Size            int64  `json:"size"`
+
+	// UserID is the file owner user ID.
+	UserID int `json:"userID"`
+
+	// GroupID is the file owner group ID.
+	GroupID int `json:"groupID"`
+
+	// MIMEType is the MIME type of the file contents.
+	MIMEType string `json:"mimeType"`
+
+	// Size is the file size in bytes.
+	Size int64 `json:"size"`
 }
 
 type auxFileMetadataEntry FileMetadataEntry
@@ -82,17 +112,31 @@ type sbomImportLegacyFileMetadataEntry struct {
 	Size            int64               `json:"Size"`
 }
 
+// FileLicense represents license information discovered within a file's contents or metadata, including the matched license text and SPDX expression.
 type FileLicense struct {
-	Value          string               `json:"value"`
-	SPDXExpression string               `json:"spdxExpression"`
-	Type           license.Type         `json:"type"`
-	Evidence       *FileLicenseEvidence `json:"evidence,omitempty"`
+	// Value is the raw license identifier or text as found in the file.
+	Value string `json:"value"`
+
+	// SPDXExpression is the parsed SPDX license expression.
+	SPDXExpression string `json:"spdxExpression"`
+
+	// Type is the license type classification (e.g., declared, concluded, discovered).
+	Type license.Type `json:"type"`
+
+	// Evidence contains supporting evidence for this license detection.
+	Evidence *FileLicenseEvidence `json:"evidence,omitempty"`
 }
 
+// FileLicenseEvidence contains supporting evidence for a license detection in a file, including the byte offset, extent, and confidence level.
 type FileLicenseEvidence struct {
+	// Confidence is the confidence score for this license detection (0-100).
 	Confidence int `json:"confidence"`
-	Offset     int `json:"offset"`
-	Extent     int `json:"extent"`
+
+	// Offset is the byte offset where the license text starts in the file.
+	Offset int `json:"offset"`
+
+	// Extent is the length of the license text in bytes.
+	Extent int `json:"extent"`
 }
 
 type intOrStringFileType struct {

syft/format/syftjson/model/linux_release.go

@@ -4,28 +4,67 @@ import (
 	"encoding/json"
 )
 
+// IDLikes represents a list of distribution IDs that this Linux distribution is similar to or derived from, as defined in os-release ID_LIKE field.
 type IDLikes []string
 
+// LinuxRelease contains Linux distribution identification and version information extracted from /etc/os-release or similar system files.
 type LinuxRelease struct {
-	PrettyName       string  `json:"prettyName,omitempty"`
-	Name             string  `json:"name,omitempty"`
-	ID               string  `json:"id,omitempty"`
-	IDLike           IDLikes `json:"idLike,omitempty"`
-	Version          string  `json:"version,omitempty"`
-	VersionID        string  `json:"versionID,omitempty"`
-	VersionCodename  string  `json:"versionCodename,omitempty"`
-	BuildID          string  `json:"buildID,omitempty"`
-	ImageID          string  `json:"imageID,omitempty"`
-	ImageVersion     string  `json:"imageVersion,omitempty"`
-	Variant          string  `json:"variant,omitempty"`
-	VariantID        string  `json:"variantID,omitempty"`
-	HomeURL          string  `json:"homeURL,omitempty"`
-	SupportURL       string  `json:"supportURL,omitempty"`
-	BugReportURL     string  `json:"bugReportURL,omitempty"`
-	PrivacyPolicyURL string  `json:"privacyPolicyURL,omitempty"`
-	CPEName          string  `json:"cpeName,omitempty"`
-	SupportEnd       string  `json:"supportEnd,omitempty"`
-	ExtendedSupport  bool    `json:"extendedSupport,omitempty"`
+	// PrettyName is a human-readable operating system name with version.
+	PrettyName string `json:"prettyName,omitempty"`
+
+	// Name is the operating system name without version information.
+	Name string `json:"name,omitempty"`
+
+	// ID is the lower-case operating system identifier (e.g., "ubuntu", "rhel").
+	ID string `json:"id,omitempty"`
+
+	// IDLike is a list of operating system IDs this distribution is similar to or derived from.
+	IDLike IDLikes `json:"idLike,omitempty"`
+
+	// Version is the operating system version including codename if available.
+	Version string `json:"version,omitempty"`
+
+	// VersionID is the operating system version number or identifier.
+	VersionID string `json:"versionID,omitempty"`
+
+	// VersionCodename is the operating system release codename (e.g., "jammy", "bullseye").
+	VersionCodename string `json:"versionCodename,omitempty"`
+
+	// BuildID is a build identifier for the operating system.
+	BuildID string `json:"buildID,omitempty"`
+
+	// ImageID is an identifier for container or cloud images.
+	ImageID string `json:"imageID,omitempty"`
+
+	// ImageVersion is the version for container or cloud images.
+	ImageVersion string `json:"imageVersion,omitempty"`
+
+	// Variant is the operating system variant name (e.g., "Server", "Workstation").
+	Variant string `json:"variant,omitempty"`
+
+	// VariantID is the lower-case operating system variant identifier.
+	VariantID string `json:"variantID,omitempty"`
+
+	// HomeURL is the homepage URL for the operating system.
+	HomeURL string `json:"homeURL,omitempty"`
+
+	// SupportURL is the support or help URL for the operating system.
+	SupportURL string `json:"supportURL,omitempty"`
+
+	// BugReportURL is the bug reporting URL for the operating system.
+	BugReportURL string `json:"bugReportURL,omitempty"`
+
+	// PrivacyPolicyURL is the privacy policy URL for the operating system.
+	PrivacyPolicyURL string `json:"privacyPolicyURL,omitempty"`
+
+	// CPEName is the Common Platform Enumeration name for the operating system.
+	CPEName string `json:"cpeName,omitempty"`
+
+	// SupportEnd is the end of support date or version identifier.
+	SupportEnd string `json:"supportEnd,omitempty"`
+
+	// ExtendedSupport indicates whether extended security or support is available.
+	ExtendedSupport bool `json:"extendedSupport,omitempty"`
 }
 
 func (s *IDLikes) UnmarshalJSON(data []byte) error {

syft/format/syftjson/model/package.go

@@ -36,22 +36,40 @@ type PackageBasicData struct {
 	PURL      string          `json:"purl"`
 }
 
+// cpes is a collection of Common Platform Enumeration identifiers for a package.
 type cpes []CPE
 
+// CPE represents a Common Platform Enumeration identifier used for matching packages to known vulnerabilities in security databases.
 type CPE struct {
-	Value  string `json:"cpe"`
+	// Value is the CPE string identifier.
+	Value string `json:"cpe"`
+
+	// Source is the source where this CPE was obtained or generated from.
 	Source string `json:"source,omitempty"`
 }
 
+// licenses is a collection of license findings associated with a package.
 type licenses []License
 
+// License represents software license information discovered for a package, including SPDX expressions and supporting evidence locations.
 type License struct {
-	Value          string          `json:"value"`
-	SPDXExpression string          `json:"spdxExpression"`
-	Type           license.Type    `json:"type"`
-	URLs           []string        `json:"urls"`
-	Locations      []file.Location `json:"locations"`
-	Contents       string          `json:"contents,omitempty"`
+	// Value is the raw license identifier or expression as found.
+	Value string `json:"value"`
+
+	// SPDXExpression is the parsed SPDX license expression.
+	SPDXExpression string `json:"spdxExpression"`
+
+	// Type is the license type classification (e.g., declared, concluded, discovered).
+	Type license.Type `json:"type"`
+
+	// URLs are URLs where license text or information can be found.
+	URLs []string `json:"urls"`
+
+	// Locations are file locations where this license was discovered.
+	Locations []file.Location `json:"locations"`
+
+	// Contents is the full license text content.
+	Contents string `json:"contents,omitempty"`
 }
 
 func newModelLicensesFromValues(licenses []string) (ml []License) {

syft/format/syftjson/model/relationship.go

@@ -1,8 +1,16 @@
 package model
 
+// Relationship represents a directed relationship between two artifacts in the SBOM, such as package-contains-file or package-depends-on-package.
 type Relationship struct {
-	Parent   string      `json:"parent"`
-	Child    string      `json:"child"`
-	Type     string      `json:"type"`
+	// Parent is the ID of the parent artifact in this relationship.
+	Parent string `json:"parent"`
+
+	// Child is the ID of the child artifact in this relationship.
+	Child string `json:"child"`
+
+	// Type is the relationship type (e.g., "contains", "dependency-of", "ancestor-of").
+	Type string `json:"type"`
+
+	// Metadata contains additional relationship-specific metadata.
 	Metadata interface{} `json:"metadata,omitempty"`
 }

syft/format/syftjson/model/source.go

@@ -11,18 +11,25 @@ import (
 	"github.com/anchore/syft/syft/source"
 )
 
-// Source object represents the thing that was cataloged
-// Note: syft currently makes no claims or runs any logic to determine the Supplier field below
-
-// Instead, the Supplier can be determined by the user of syft and passed as a config or flag to help fulfill
-// the NTIA minimum elements. For mor information see the NTIA framing document below
-// https://www.ntia.gov/files/ntia/publications/framingsbom_20191112.pdf
+// Source represents the artifact that was analyzed to generate this SBOM, such as a container image, directory, or file archive.
+// The Supplier field can be provided by users to fulfill NTIA minimum elements requirements.
 type Source struct {
-	ID       string      `json:"id"`
-	Name     string      `json:"name"`
-	Version  string      `json:"version"`
-	Supplier string      `json:"supplier,omitempty"`
-	Type     string      `json:"type"`
+	// ID is a unique identifier for the analyzed source artifact.
+	ID string `json:"id"`
+
+	// Name is the name of the analyzed artifact (e.g., image name, directory path).
+	Name string `json:"name"`
+
+	// Version is the version of the analyzed artifact (e.g., image tag).
+	Version string `json:"version"`
+
+	// Supplier is supplier information, which can be user-provided for NTIA minimum elements compliance.
+	Supplier string `json:"supplier,omitempty"`
+
+	// Type is the source type (e.g., "image", "directory", "file").
+	Type string `json:"type"`
+
+	// Metadata contains additional source-specific metadata.
 	Metadata interface{} `json:"metadata"`
 }
 

syft/get_source_config_test.go

@@ -0,0 +1,37 @@
+package syft
+
+import (
+	"testing"
+
+	"github.com/anchore/stereoscope"
+	"github.com/anchore/syft/syft/source/sourceproviders"
+)
+
+func TestGetProviders_DefaultImagePullSource(t *testing.T) {
+	userInput := ""
+	cfg := &GetSourceConfig{DefaultImagePullSource: stereoscope.RegistryTag}
+	allSourceProviders := sourceproviders.All(userInput, cfg.SourceProviderConfig)
+
+	providers, err := cfg.getProviders(userInput)
+	if err != nil {
+		t.Errorf("Expected no error for DefaultImagePullSource parameter, got: %v", err)
+	}
+
+	if len(providers) != len(allSourceProviders) {
+		t.Errorf("Expected %d providers, got %d", len(allSourceProviders), len(providers))
+	}
+}
+
+func TestGetProviders_Sources(t *testing.T) {
+	userInput := ""
+	cfg := &GetSourceConfig{Sources: []string{stereoscope.RegistryTag}}
+
+	providers, err := cfg.getProviders(userInput)
+	if err != nil {
+		t.Errorf("Expected no error for Sources parameter, got: %v", err)
+	}
+
+	if len(providers) != 1 {
+		t.Errorf("Expected 1 providers, got %d", len(providers))
+	}
+}

syft/internal/fileresolver/directory.go

@@ -19,16 +19,16 @@ type Directory struct {
 	indexer *directoryIndexer
 }
 
-func NewFromDirectory(root string, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
-	r, err := newFromDirectoryWithoutIndex(root, base, pathFilters...)
+func NewFromDirectory(root, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
+	resolver, err := newFromDirectoryWithoutIndex(root, base, pathFilters...)
 	if err != nil {
 		return nil, err
 	}
 
-	return r, r.buildIndex()
+	return resolver, resolver.buildIndex()
 }
 
-func newFromDirectoryWithoutIndex(root string, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
+func newFromDirectoryWithoutIndex(root, base string, pathFilters ...PathIndexVisitor) (*Directory, error) {
 	chroot, err := NewChrootContextFromCWD(root, base)
 	if err != nil {
 		return nil, fmt.Errorf("unable to interpret chroot context: %w", err)
@@ -66,6 +66,6 @@ func (r *Directory) buildIndex() error {
 }
 
 // Stringer to represent a directory path data source
-func (r Directory) String() string {
+func (r *Directory) String() string {
 	return fmt.Sprintf("dir:%s", r.path)
 }

syft/internal/fileresolver/directory_indexer.go

@@ -322,7 +322,7 @@ func (r directoryIndexer) addDirectoryToIndex(p string, info os.FileInfo) error
 		return err
 	}
 
-	metadata := file.NewMetadataFromPath(p, info)
+	metadata := NewMetadataFromPath(p, info)
 	r.index.Add(*ref, metadata)
 
 	return nil
@@ -334,7 +334,7 @@ func (r directoryIndexer) addFileToIndex(p string, info os.FileInfo) error {
 		return err
 	}
 
-	metadata := file.NewMetadataFromPath(p, info)
+	metadata := NewMetadataFromPath(p, info)
 	r.index.Add(*ref, metadata)
 
 	return nil
@@ -416,7 +416,7 @@ func (r directoryIndexer) addSymlinkToIndex(p string, info os.FileInfo) (string,
 		targetAbsPath = filepath.Clean(filepath.Join(path.Dir(p), linkTarget))
 	}
 
-	metadata := file.NewMetadataFromPath(p, info)
+	metadata := NewMetadataFromPath(p, info)
 	metadata.LinkDestination = linkTarget
 	r.index.Add(*ref, metadata)
 

syft/internal/fileresolver/file.go

@@ -17,17 +17,31 @@ type File struct {
 	indexer *fileIndexer
 }
 
-// parent should be the symlink free absolute path to the parent directory
+// NewFromFile single file analyser
 // path is the filepath of the file we're creating content access for
-func NewFromFile(parent, path string, pathFilters ...PathIndexVisitor) (*File, error) {
-	chroot, err := NewChrootContextFromCWD(parent, parent)
+func NewFromFile(path string, pathFilters ...PathIndexVisitor) (*File, error) {
+	resolver, err := newFromFileWithoutIndex(path, pathFilters...)
+	if err != nil {
+		return nil, err
+	}
+
+	return resolver, resolver.buildIndex()
+}
+
+func newFromFileWithoutIndex(path string, pathFilters ...PathIndexVisitor) (*File, error) {
+	absParentDir, err := absoluteSymlinkFreePathToParent(path)
+	if err != nil {
+		return nil, err
+	}
+
+	chroot, err := NewChrootContextFromCWD(absParentDir, absParentDir)
 	if err != nil {
 		return nil, fmt.Errorf("unable to interpret chroot context: %w", err)
 	}
 
 	cleanBase := chroot.Base()
 
-	file := &File{
+	return &File{
 		path: path,
 		FiletreeResolver: FiletreeResolver{
 			Chroot: *chroot,
@@ -36,9 +50,7 @@ func NewFromFile(parent, path string, pathFilters ...PathIndexVisitor) (*File, e
 			Opener: nativeOSFileOpener,
 		},
 		indexer: newFileIndexer(path, cleanBase, pathFilters...),
-	}
-
-	return file, file.buildIndex()
+	}, nil
 }
 
 func (r *File) buildIndex() error {
@@ -58,6 +70,6 @@ func (r *File) buildIndex() error {
 }
 
 // Stringer to represent a file path data source
-func (r File) String() string {
+func (r *File) String() string {
 	return fmt.Sprintf("file:%s", r.path)
 }

syft/internal/fileresolver/file_indexer.go

@@ -173,7 +173,7 @@ func (r *fileIndexer) addDirectoryToIndex(path string, info os.FileInfo) error {
 		return err
 	}
 
-	metadata := file.NewMetadataFromPath(path, info)
+	metadata := NewMetadataFromPath(path, info)
 	r.index.Add(*ref, metadata)
 
 	return nil
@@ -185,7 +185,7 @@ func (r *fileIndexer) addFileToIndex(path string, info os.FileInfo) error {
 		return err
 	}
 
-	metadata := file.NewMetadataFromPath(path, info)
+	metadata := NewMetadataFromPath(path, info)
 	r.index.Add(*ref, metadata)
 
 	return nil

syft/internal/fileresolver/filetree_resolver_test.go

@@ -1384,9 +1384,10 @@ func TestFileResolver_FilesByPath(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, tt.filePath)
+			resolver, err := NewFromFile(tt.filePath)
 			require.NoError(t, err)
 			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 			refs, err := resolver.FilesByPath(tt.fileByPathInput)
 			require.NoError(t, err)
@@ -1431,8 +1432,11 @@ func TestFileResolver_MultipleFilesByPath(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, filePath)
+			resolver, err := NewFromFile(filePath)
 			assert.NoError(t, err)
+			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 			refs, err := resolver.FilesByPath(tt.input...)
 			assert.NoError(t, err)
 
@@ -1449,8 +1453,11 @@ func TestFileResolver_FilesByGlob(t *testing.T) {
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
 
-	resolver, err := NewFromFile(parentPath, filePath)
+	resolver, err := NewFromFile(filePath)
 	assert.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 	refs, err := resolver.FilesByGlob("**/*.txt")
 	assert.NoError(t, err)
 
@@ -1476,8 +1483,11 @@ func Test_fileResolver_FilesByMIMEType(t *testing.T) {
 			require.NoError(t, err)
 			require.NotNil(t, parentPath)
 
-			resolver, err := NewFromFile(parentPath, filePath)
+			resolver, err := NewFromFile(filePath)
 			assert.NoError(t, err)
+			require.NotNil(t, resolver)
+			assert.Equal(t, resolver.Chroot.Base(), parentPath)
+
 			locations, err := resolver.FilesByMIMEType(test.mimeType)
 			assert.NoError(t, err)
 			assert.Equal(t, test.expectedPaths.Size(), len(locations))
@@ -1497,10 +1507,12 @@ func Test_fileResolver_FileContentsByLocation(t *testing.T) {
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
 
-	r, err := NewFromFile(parentPath, filePath)
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
-	exists, existingPath, err := r.Tree.File(stereoscopeFile.Path(filepath.Join(cwd, "test-fixtures/image-simple/file-1.txt")))
+	exists, existingPath, err := resolver.Tree.File(stereoscopeFile.Path(filepath.Join(cwd, "test-fixtures/image-simple/file-1.txt")))
 	require.True(t, exists)
 	require.NoError(t, err)
 	require.True(t, existingPath.HasReference())
@@ -1525,7 +1537,7 @@ func Test_fileResolver_FileContentsByLocation(t *testing.T) {
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {
 
-			actual, err := r.FileContentsByLocation(test.location)
+			actual, err := resolver.FileContentsByLocation(test.location)
 			if test.err {
 				require.Error(t, err)
 				return
@@ -1546,8 +1558,11 @@ func TestFileResolver_AllLocations_errorOnDirRequest(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	var dirLoc *file.Location
 	ctx, cancel := context.WithCancel(context.Background())
@@ -1575,8 +1590,11 @@ func TestFileResolver_AllLocations(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	paths := strset.New()
 	for loc := range resolver.AllLocations(context.Background()) {
@@ -1600,8 +1618,11 @@ func Test_FileResolver_AllLocationsDoesNotLeakGoRoutine(t *testing.T) {
 	parentPath, err := absoluteSymlinkFreePathToParent(filePath)
 	require.NoError(t, err)
 	require.NotNil(t, parentPath)
-	resolver, err := NewFromFile(parentPath, filePath)
+
+	resolver, err := NewFromFile(filePath)
 	require.NoError(t, err)
+	require.NotNil(t, resolver)
+	assert.Equal(t, resolver.Chroot.Base(), parentPath)
 
 	require.NoError(t, err)
 	ctx, cancel := context.WithCancel(context.Background())

syft/internal/fileresolver/get_xid.go

@@ -0,0 +1,20 @@
+//go:build !windows
+
+package fileresolver
+
+import (
+	"os"
+	"syscall"
+)
+
+// getXid is the UID GID system info for unix
+func getXid(info os.FileInfo) (uid, gid int) {
+	uid = -1
+	gid = -1
+	if stat, ok := info.Sys().(*syscall.Stat_t); ok {
+		uid = int(stat.Uid)
+		gid = int(stat.Gid)
+	}
+
+	return uid, gid
+}

syft/internal/fileresolver/get_xid_win.go

@@ -0,0 +1,12 @@
+//go:build windows
+
+package fileresolver
+
+import (
+	"os"
+)
+
+// getXid is a placeholder for windows file information
+func getXid(info os.FileInfo) (uid, gid int) {
+	return -1, -1
+}

syft/internal/fileresolver/metadata.go

@@ -0,0 +1,44 @@
+package fileresolver
+
+import (
+	"os"
+
+	"github.com/anchore/stereoscope/pkg/file"
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/syft/internal/windows"
+)
+
+func NewMetadataFromPath(path string, info os.FileInfo) file.Metadata {
+	var mimeType string
+	uid, gid := getXid(info)
+
+	ty := file.TypeFromMode(info.Mode())
+
+	if ty == file.TypeRegular {
+		usablePath := path
+		// denormalize the path back to windows so we can open the file
+		if windows.HostRunningOnWindows() {
+			usablePath = windows.FromPosix(usablePath)
+		}
+
+		f, err := os.Open(usablePath)
+		if err != nil {
+			// TODO: it may be that the file is inaccessible, however, this is not an error or a warning. In the future we need to track these as known-unknowns
+			f = nil
+		} else {
+			defer internal.CloseAndLogError(f, usablePath)
+		}
+
+		mimeType = file.MIMEType(f)
+	}
+
+	return file.Metadata{
+		FileInfo: info,
+		Path:     path,
+		Type:     ty,
+		// unsupported across platforms
+		UserID:   uid,
+		GroupID:  gid,
+		MIMEType: mimeType,
+	}
+}

syft/internal/fileresolver/metadata_test.go

@@ -0,0 +1,51 @@
+package fileresolver
+
+import (
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/stereoscope/pkg/file"
+)
+
+func TestFileMetadataFromPath(t *testing.T) {
+
+	tests := []struct {
+		path             string
+		expectedType     file.Type
+		expectedMIMEType string
+	}{
+		{
+			path:             "test-fixtures/symlinks-simple/readme",
+			expectedType:     file.TypeRegular,
+			expectedMIMEType: "text/plain",
+		},
+		{
+			path:             "test-fixtures/symlinks-simple/link_to_new_readme",
+			expectedType:     file.TypeSymLink,
+			expectedMIMEType: "",
+		},
+		{
+			path:             "test-fixtures/symlinks-simple/link_to_link_to_new_readme",
+			expectedType:     file.TypeSymLink,
+			expectedMIMEType: "",
+		},
+		{
+			path:             "test-fixtures/symlinks-simple",
+			expectedType:     file.TypeDirectory,
+			expectedMIMEType: "",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.path, func(t *testing.T) {
+			info, err := os.Lstat(test.path)
+			require.NoError(t, err)
+
+			actual := NewMetadataFromPath(test.path, info)
+			assert.Equal(t, test.expectedMIMEType, actual.MIMEType, "unexpected MIME type for %s", test.path)
+			assert.Equal(t, test.expectedType, actual.Type, "unexpected type for %s", test.path)
+		})
+	}
+}

syft/pkg/alpm.go

@@ -58,6 +58,7 @@ type AlpmDBEntry struct {
 	Depends []string `mapstructure:"depends" json:"depends,omitempty"`
 }
 
+// AlpmFileRecord represents a single file entry within an Arch Linux package with its associated metadata tracked by pacman.
 type AlpmFileRecord struct {
 	// Path is the file path relative to the filesystem root
 	Path string `mapstruture:"path" json:"path,omitempty"`

syft/pkg/cataloger/.gitignore

@@ -0,0 +1,2 @@
+# these are generated by pkgtest helpers, no need to check them in
+**/test-fixtures/test-observations.json

syft/pkg/cataloger/ai/cataloger.go

@@ -0,0 +1,16 @@
+/*
+Package ai provides concrete Cataloger implementations for AI artifacts and machine learning models,
+including support for GGUF (GPT-Generated Unified Format) model files.
+*/
+package ai
+
+import (
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+)
+
+// NewGGUFCataloger returns a new cataloger instance for GGUF model files.
+func NewGGUFCataloger() pkg.Cataloger {
+	return generic.NewCataloger("gguf-cataloger").
+		WithParserByGlobs(parseGGUFModel, "**/*.gguf")
+}

syft/pkg/cataloger/ai/cataloger_test.go

@@ -0,0 +1,140 @@
+package ai
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/pkgtest"
+)
+
+func TestGGUFCataloger_Globs(t *testing.T) {
+	tests := []struct {
+		name     string
+		fixture  string
+		expected []string
+	}{
+		{
+			name:    "obtain gguf files",
+			fixture: "test-fixtures/glob-paths",
+			expected: []string{
+				"models/model.gguf",
+			},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, test.fixture).
+				ExpectsResolverContentQueries(test.expected).
+				TestCataloger(t, NewGGUFCataloger())
+		})
+	}
+}
+
+func TestGGUFCataloger(t *testing.T) {
+	tests := []struct {
+		name                  string
+		setup                 func(t *testing.T) string
+		expectedPackages      []pkg.Package
+		expectedRelationships []artifact.Relationship
+	}{
+		{
+			name: "catalog single GGUF file",
+			setup: func(t *testing.T) string {
+				dir := t.TempDir()
+				data := newTestGGUFBuilder().
+					withVersion(3).
+					withStringKV("general.architecture", "llama").
+					withStringKV("general.name", "llama3-8b").
+					withStringKV("general.version", "3.0").
+					withStringKV("general.license", "Apache-2.0").
+					withStringKV("general.quantization", "Q4_K_M").
+					withUint64KV("general.parameter_count", 8030000000).
+					withStringKV("general.some_random_kv", "foobar").
+					build()
+
+				path := filepath.Join(dir, "llama3-8b.gguf")
+				os.WriteFile(path, data, 0644)
+				return dir
+			},
+			expectedPackages: []pkg.Package{
+				{
+					Name:    "llama3-8b",
+					Version: "3.0",
+					Type:    pkg.ModelPkg,
+					Licenses: pkg.NewLicenseSet(
+						pkg.NewLicenseFromFields("Apache-2.0", "", nil),
+					),
+					Metadata: pkg.GGUFFileHeader{
+						Architecture:          "llama",
+						Quantization:          "Unknown",
+						Parameters:            0,
+						GGUFVersion:           3,
+						TensorCount:           0,
+						MetadataKeyValuesHash: "6e3d368066455ce4",
+						RemainingKeyValues: map[string]interface{}{
+							"general.some_random_kv": "foobar",
+						},
+					},
+				},
+			},
+			expectedRelationships: nil,
+		},
+		{
+			name: "catalog GGUF file with minimal metadata",
+			setup: func(t *testing.T) string {
+				dir := t.TempDir()
+				data := newTestGGUFBuilder().
+					withVersion(3).
+					withStringKV("general.architecture", "gpt2").
+					withStringKV("general.name", "gpt2-small").
+					withStringKV("gpt2.context_length", "1024").
+					withUint32KV("gpt2.embedding_length", 768).
+					build()
+
+				path := filepath.Join(dir, "gpt2-small.gguf")
+				os.WriteFile(path, data, 0644)
+				return dir
+			},
+			expectedPackages: []pkg.Package{
+				{
+					Name:     "gpt2-small",
+					Version:  "",
+					Type:     pkg.ModelPkg,
+					Licenses: pkg.NewLicenseSet(),
+					Metadata: pkg.GGUFFileHeader{
+						Architecture:          "gpt2",
+						Quantization:          "Unknown",
+						Parameters:            0,
+						GGUFVersion:           3,
+						TensorCount:           0,
+						MetadataKeyValuesHash: "9dc6f23591062a27",
+						RemainingKeyValues: map[string]interface{}{
+							"gpt2.context_length":   "1024",
+							"gpt2.embedding_length": uint32(768),
+						},
+					},
+				},
+			},
+			expectedRelationships: nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			fixtureDir := tt.setup(t)
+
+			// Use pkgtest to catalog and compare
+			pkgtest.NewCatalogTester().
+				FromDirectory(t, fixtureDir).
+				Expects(tt.expectedPackages, tt.expectedRelationships).
+				IgnoreLocationLayer().
+				IgnorePackageFields("FoundBy", "Locations").
+				TestCataloger(t, NewGGUFCataloger())
+		})
+	}
+}

syft/pkg/cataloger/ai/package.go

@@ -0,0 +1,22 @@
+package ai
+
+import (
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+)
+
+func newGGUFPackage(metadata *pkg.GGUFFileHeader, modelName, version, license string, locations ...file.Location) pkg.Package {
+	p := pkg.Package{
+		Name:      modelName,
+		Version:   version,
+		Locations: file.NewLocationSet(locations...),
+		Type:      pkg.ModelPkg,
+		Licenses:  pkg.NewLicenseSet(pkg.NewLicensesFromValues(license)...),
+		Metadata:  *metadata,
+		// NOTE: PURL is intentionally not set as the package-url spec
+		// has not yet finalized support for ML model packages
+	}
+	p.SetID()
+
+	return p
+}

syft/pkg/cataloger/ai/package_test.go

@@ -0,0 +1,121 @@
+package ai
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/pkgtest"
+)
+
+func TestNewGGUFPackage(t *testing.T) {
+	tests := []struct {
+		name     string
+		metadata *pkg.GGUFFileHeader
+		input    struct {
+			modelName string
+			version   string
+			license   string
+			locations []file.Location
+		}
+		expected pkg.Package
+	}{
+		{
+			name: "complete GGUF package with all fields",
+			input: struct {
+				modelName string
+				version   string
+				license   string
+				locations []file.Location
+			}{
+				modelName: "llama3-8b",
+				version:   "3.0",
+				license:   "Apache-2.0",
+				locations: []file.Location{file.NewLocation("/models/llama3-8b.gguf")},
+			},
+			metadata: &pkg.GGUFFileHeader{
+				Architecture: "llama",
+				Quantization: "Q4_K_M",
+				Parameters:   8030000000,
+				GGUFVersion:  3,
+				TensorCount:  291,
+				RemainingKeyValues: map[string]any{
+					"general.random_kv": "foobar",
+				},
+			},
+			expected: pkg.Package{
+				Name:    "llama3-8b",
+				Version: "3.0",
+				Type:    pkg.ModelPkg,
+				Licenses: pkg.NewLicenseSet(
+					pkg.NewLicenseFromFields("Apache-2.0", "", nil),
+				),
+				Metadata: pkg.GGUFFileHeader{
+					Architecture: "llama",
+					Quantization: "Q4_K_M",
+					Parameters:   8030000000,
+					GGUFVersion:  3,
+					TensorCount:  291,
+					RemainingKeyValues: map[string]any{
+						"general.random_kv": "foobar",
+					},
+				},
+				Locations: file.NewLocationSet(file.NewLocation("/models/llama3-8b.gguf")),
+			},
+		},
+		{
+			name: "minimal GGUF package",
+			input: struct {
+				modelName string
+				version   string
+				license   string
+				locations []file.Location
+			}{
+				modelName: "gpt2-small",
+				version:   "1.0",
+				license:   "MIT",
+				locations: []file.Location{file.NewLocation("/models/simple.gguf")},
+			},
+			metadata: &pkg.GGUFFileHeader{
+				Architecture: "gpt2",
+				GGUFVersion:  3,
+				TensorCount:  50,
+			},
+			expected: pkg.Package{
+				Name:    "gpt2-small",
+				Version: "1.0",
+				Type:    pkg.ModelPkg,
+				Licenses: pkg.NewLicenseSet(
+					pkg.NewLicenseFromFields("MIT", "", nil),
+				),
+				Metadata: pkg.GGUFFileHeader{
+					Architecture: "gpt2",
+					GGUFVersion:  3,
+					TensorCount:  50,
+				},
+				Locations: file.NewLocationSet(file.NewLocation("/models/simple.gguf")),
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			actual := newGGUFPackage(
+				tt.metadata,
+				tt.input.modelName,
+				tt.input.version,
+				tt.input.license,
+				tt.input.locations...,
+			)
+
+			// Verify metadata type
+			_, ok := actual.Metadata.(pkg.GGUFFileHeader)
+			require.True(t, ok, "metadata should be GGUFFileHeader")
+
+			// Use AssertPackagesEqual for comprehensive comparison
+			pkgtest.AssertPackagesEqual(t, tt.expected, actual)
+		})
+	}
+}

syft/pkg/cataloger/ai/parse_gguf.go

@@ -0,0 +1,63 @@
+package ai
+
+import (
+	"encoding/binary"
+	"fmt"
+	"io"
+
+	gguf_parser "github.com/gpustack/gguf-parser-go"
+)
+
+// GGUF file format constants
+const (
+	ggufMagicNumber = 0x46554747       // "GGUF" in little-endian
+	maxHeaderSize   = 50 * 1024 * 1024 // 50MB for large tokenizer vocabularies
+)
+
+// copyHeader copies the GGUF header from the reader to the writer.
+// It validates the magic number first, then copies the rest of the data.
+// The reader should be wrapped with io.LimitedReader to prevent OOM issues.
+func copyHeader(w io.Writer, r io.Reader) error {
+	// Read initial chunk to validate magic number
+	// GGUF format: magic(4) + version(4) + tensor_count(8) + metadata_kv_count(8) + metadata_kvs + tensors_info
+	initialBuf := make([]byte, 24) // Enough for magic, version, tensor count, and kv count
+	if _, err := io.ReadFull(r, initialBuf); err != nil {
+		return fmt.Errorf("failed to read GGUF header prefix: %w", err)
+	}
+
+	// Verify magic number
+	magic := binary.LittleEndian.Uint32(initialBuf[0:4])
+	if magic != ggufMagicNumber {
+		return fmt.Errorf("invalid GGUF magic number: 0x%08X", magic)
+	}
+
+	// Write the initial buffer to the writer
+	if _, err := w.Write(initialBuf); err != nil {
+		return fmt.Errorf("failed to write GGUF header prefix: %w", err)
+	}
+
+	// Copy the rest of the header from reader to writer
+	// The LimitedReader will return EOF once maxHeaderSize is reached
+	if _, err := io.Copy(w, r); err != nil {
+		return fmt.Errorf("failed to copy GGUF header: %w", err)
+	}
+
+	return nil
+}
+
+// Helper to convert gguf_parser metadata to simpler types
+func convertGGUFMetadataKVs(kvs gguf_parser.GGUFMetadataKVs) map[string]interface{} {
+	result := make(map[string]interface{})
+
+	for _, kv := range kvs {
+		// Skip standard fields that are extracted separately
+		switch kv.Key {
+		case "general.architecture", "general.name", "general.license",
+			"general.version", "general.parameter_count", "general.quantization":
+			continue
+		}
+		result[kv.Key] = kv.Value
+	}
+
+	return result
+}

syft/pkg/cataloger/ai/parse_gguf_model.go

@@ -0,0 +1,135 @@
+package ai
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	"github.com/cespare/xxhash/v2"
+	gguf_parser "github.com/gpustack/gguf-parser-go"
+
+	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/log"
+	"github.com/anchore/syft/internal/unknown"
+	"github.com/anchore/syft/syft/artifact"
+	"github.com/anchore/syft/syft/file"
+	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/generic"
+)
+
+// parseGGUFModel parses a GGUF model file and returns the discovered package.
+// This implementation only reads the header portion of the file, not the entire model.
+func parseGGUFModel(_ context.Context, _ file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+	defer internal.CloseAndLogError(reader, reader.Path())
+
+	// Create a temporary file for the library to parse
+	// The library requires a file path, so we create a temp file
+	tempFile, err := os.CreateTemp("", "syft-gguf-*.gguf")
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to create temp file: %w", err)
+	}
+	tempPath := tempFile.Name()
+	defer os.Remove(tempPath)
+
+	// Copy and validate the GGUF file header using LimitedReader to prevent OOM
+	// We use LimitedReader to cap reads at maxHeaderSize (50MB)
+	limitedReader := &io.LimitedReader{R: reader, N: maxHeaderSize}
+	if err := copyHeader(tempFile, limitedReader); err != nil {
+		tempFile.Close()
+		return nil, nil, fmt.Errorf("failed to copy GGUF header: %w", err)
+	}
+	tempFile.Close()
+
+	// Parse using gguf-parser-go with options to skip unnecessary data
+	ggufFile, err := gguf_parser.ParseGGUFFile(tempPath,
+		gguf_parser.SkipLargeMetadata(),
+	)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to parse GGUF file: %w", err)
+	}
+
+	// Extract metadata
+	metadata := ggufFile.Metadata()
+
+	// Extract version separately (will be set on Package.Version)
+	modelVersion := extractVersion(ggufFile.Header.MetadataKV)
+
+	// Convert to syft metadata structure
+	syftMetadata := &pkg.GGUFFileHeader{
+		Architecture:          metadata.Architecture,
+		Quantization:          metadata.FileTypeDescriptor,
+		Parameters:            uint64(metadata.Parameters),
+		GGUFVersion:           uint32(ggufFile.Header.Version),
+		TensorCount:           ggufFile.Header.TensorCount,
+		RemainingKeyValues:    convertGGUFMetadataKVs(ggufFile.Header.MetadataKV),
+		MetadataKeyValuesHash: computeKVMetadataHash(ggufFile.Header.MetadataKV),
+	}
+
+	// If model name is not in metadata, use filename
+	if metadata.Name == "" {
+		metadata.Name = extractModelNameFromPath(reader.Path())
+	}
+
+	// Create package from metadata
+	p := newGGUFPackage(
+		syftMetadata,
+		metadata.Name,
+		modelVersion,
+		metadata.License,
+		reader.WithAnnotation(pkg.EvidenceAnnotationKey, pkg.PrimaryEvidenceAnnotation),
+	)
+
+	return []pkg.Package{p}, nil, unknown.IfEmptyf([]pkg.Package{p}, "unable to parse GGUF file")
+}
+
+// computeKVMetadataHash computes a stable hash of the KV metadata for use as a global identifier
+func computeKVMetadataHash(metadata gguf_parser.GGUFMetadataKVs) string {
+	// Sort the KV pairs by key for stable hashing
+	sortedKVs := make([]gguf_parser.GGUFMetadataKV, len(metadata))
+	copy(sortedKVs, metadata)
+	sort.Slice(sortedKVs, func(i, j int) bool {
+		return sortedKVs[i].Key < sortedKVs[j].Key
+	})
+
+	// Marshal sorted KVs to JSON for stable hashing
+	jsonBytes, err := json.Marshal(sortedKVs)
+	if err != nil {
+		log.Debugf("failed to marshal metadata for hashing: %v", err)
+		return ""
+	}
+
+	// Compute xxhash
+	hash := xxhash.Sum64(jsonBytes)
+	return fmt.Sprintf("%016x", hash) // 16 hex chars (64 bits)
+}
+
+// extractVersion attempts to extract version from metadata KV pairs
+func extractVersion(kvs gguf_parser.GGUFMetadataKVs) string {
+	for _, kv := range kvs {
+		if kv.Key == "general.version" {
+			if v, ok := kv.Value.(string); ok && v != "" {
+				return v
+			}
+		}
+	}
+	return ""
+}
+
+// extractModelNameFromPath extracts the model name from the file path
+func extractModelNameFromPath(path string) string {
+	// Get the base filename
+	base := filepath.Base(path)
+
+	// Remove .gguf extension
+	name := strings.TrimSuffix(base, ".gguf")
+
+	return name
+}
+
+// integrity check
+var _ generic.Parser = parseGGUFModel

syft/pkg/cataloger/ai/test_helpers_test.go

@@ -0,0 +1,128 @@
+package ai
+
+import (
+	"bytes"
+	"encoding/binary"
+)
+
+// GGUF type constants for test builder
+// https://github.com/ggml-org/ggml/blob/master/docs/gguf.md
+const (
+	ggufMagic       = 0x46554747 // "GGUF" in little-endian
+	ggufTypeUint8   = 0
+	ggufTypeInt8    = 1
+	ggufTypeUint16  = 2
+	ggufTypeInt16   = 3
+	ggufTypeUint32  = 4
+	ggufTypeInt32   = 5
+	ggufTypeFloat32 = 6
+	ggufTypeBool    = 7
+	ggufTypeString  = 8
+	ggufTypeArray   = 9
+	ggufTypeUint64  = 10
+	ggufTypeInt64   = 11
+	ggufTypeFloat64 = 12
+)
+
+// testGGUFBuilder helps build GGUF files for testing
+type testGGUFBuilder struct {
+	buf         *bytes.Buffer
+	version     uint32
+	tensorCount uint64
+	kvPairs     []testKVPair
+}
+
+type testKVPair struct {
+	key       string
+	valueType uint32
+	value     interface{}
+}
+
+func newTestGGUFBuilder() *testGGUFBuilder {
+	return &testGGUFBuilder{
+		buf:         new(bytes.Buffer),
+		version:     3,
+		tensorCount: 0,
+		kvPairs:     []testKVPair{},
+	}
+}
+
+func (b *testGGUFBuilder) withVersion(v uint32) *testGGUFBuilder {
+	b.version = v
+	return b
+}
+
+func (b *testGGUFBuilder) withTensorCount(count uint64) *testGGUFBuilder {
+	b.tensorCount = count
+	return b
+}
+
+func (b *testGGUFBuilder) withStringKV(key, value string) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeString, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) withUint64KV(key string, value uint64) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeUint64, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) withUint32KV(key string, value uint32) *testGGUFBuilder {
+	b.kvPairs = append(b.kvPairs, testKVPair{key: key, valueType: ggufTypeUint32, value: value})
+	return b
+}
+
+func (b *testGGUFBuilder) writeString(s string) {
+	binary.Write(b.buf, binary.LittleEndian, uint64(len(s)))
+	b.buf.WriteString(s)
+}
+
+func (b *testGGUFBuilder) build() []byte {
+	// Write magic number "GGUF"
+	binary.Write(b.buf, binary.LittleEndian, uint32(ggufMagic))
+
+	// Write version
+	binary.Write(b.buf, binary.LittleEndian, b.version)
+
+	// Write tensor count
+	binary.Write(b.buf, binary.LittleEndian, b.tensorCount)
+
+	// Write KV count
+	binary.Write(b.buf, binary.LittleEndian, uint64(len(b.kvPairs)))
+
+	// Write KV pairs
+	for _, kv := range b.kvPairs {
+		// Write key
+		b.writeString(kv.key)
+		// Write value type
+		binary.Write(b.buf, binary.LittleEndian, kv.valueType)
+		// Write value based on type
+		switch kv.valueType {
+		case ggufTypeString:
+			b.writeString(kv.value.(string))
+		case ggufTypeUint32:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint32))
+		case ggufTypeUint64:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint64))
+		case ggufTypeUint8:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(uint8))
+		case ggufTypeInt32:
+			binary.Write(b.buf, binary.LittleEndian, kv.value.(int32))
+		case ggufTypeBool:
+			var v uint8
+			if kv.value.(bool) {
+				v = 1
+			}
+			binary.Write(b.buf, binary.LittleEndian, v)
+		}
+	}
+
+	return b.buf.Bytes()
+}
+
+// buildInvalidMagic creates a file with invalid magic number
+func (b *testGGUFBuilder) buildInvalidMagic() []byte {
+	buf := new(bytes.Buffer)
+	binary.Write(buf, binary.LittleEndian, uint32(0x12345678))
+	return buf.Bytes()
+}

syft/pkg/cataloger/binary/classifier_cataloger_test.go

@@ -1403,6 +1403,22 @@ func Test_Cataloger_PositiveCases(t *testing.T) {
 				Metadata:  metadata("ffmpeg-library"),
 			},
 		},
+		{
+			logicalFixture: "elixir/1.19.1/linux-amd64",
+			expected: pkg.Package{
+				Name:      "elixir",
+				Version:   "1.19.1",
+				Type:      "binary",
+				PURL:      "pkg:generic/elixir@1.19.1",
+				Locations: locations("elixir", "lib/elixir/ebin/elixir.app"),
+				Metadata: pkg.BinarySignature{
+					Matches: []pkg.ClassifierMatch{
+						match("elixir-binary", "elixir"),
+						match("elixir-library", "lib/elixir/ebin/elixir.app"),
+					},
+				},
+			},
+		},
 	}
 
 	for _, test := range tests {

syft/pkg/cataloger/binary/classifiers.go

@@ -663,6 +663,26 @@ func DefaultClassifiers() []binutils.Classifier {
 			PURL:    mustPURL("pkg:generic/ffmpeg@version"),
 			CPEs:    singleCPE("cpe:2.3:a:ffmpeg:ffmpeg:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
 		},
+		{
+			Class:    "elixir-binary",
+			FileGlob: "**/elixir",
+			EvidenceMatcher: m.FileContentsVersionMatcher(
+				`(?m)ELIXIR_VERSION=(?P<version>[0-9]+\.[0-9]+\.[0-9]+)`),
+			Package: "elixir",
+			PURL:    mustPURL("pkg:generic/elixir@version"),
+			CPEs: []cpe.CPE{
+				cpe.Must("cpe:2.3:a:elixir-lang:elixir:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+			},
+		},
+		{
+			Class:    "elixir-library",
+			FileGlob: "**/elixir/ebin/elixir.app",
+			EvidenceMatcher: m.FileContentsVersionMatcher(
+				`(?m)\{vsn,"(?P<version>[0-9]+\.[0-9]+\.[0-9]+(-[a-z0-9]+)?)"\}`),
+			Package: "elixir",
+			PURL:    mustPURL("pkg:generic/elixir@version"),
+			CPEs:    singleCPE("cpe:2.3:a:elixir-lang:elixir:*:*:*:*:*:*:*:*", cpe.NVDDictionaryLookupSource),
+		},
 	}
 
 	return append(classifiers, defaultJavaClassifiers()...)

syft/pkg/cataloger/binary/pe_package.go

@@ -6,6 +6,7 @@ import (
 	"sort"
 	"strings"
 
+	packageurl "github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
 )
@@ -32,6 +33,19 @@ func newPEPackage(versionResources map[string]string, f file.Location) pkg.Packa
 		Metadata:  newPEBinaryVersionResourcesFromMap(versionResources),
 	}
 
+	// If this appears to be Ghostscript, emit a canonical generic purl
+	// Example expected: pkg:generic/ghostscript@<version>
+	prod := strings.ToLower(spaceNormalize(versionResources["ProductName"]))
+	if prod == "" {
+		// fall back to FileDescription if ProductName is missing
+		prod = strings.ToLower(spaceNormalize(versionResources["FileDescription"]))
+	}
+	if p.Version != "" && strings.Contains(prod, "ghostscript") {
+		// build a generic PURL for ghostscript
+		purl := packageurl.NewPackageURL(packageurl.TypeGeneric, "", "ghostscript", p.Version, nil, "").ToString()
+		p.PURL = purl
+	}
+
 	p.SetID()
 
 	return p

syft/pkg/cataloger/binary/pe_package_test.go

@@ -0,0 +1,24 @@
+package binary
+
+import (
+	"testing"
+
+	"github.com/anchore/syft/syft/file"
+)
+
+func TestGhostscriptPEGeneratesGenericPURL(t *testing.T) {
+	vr := map[string]string{
+		"CompanyName":     "Artifex Software, Inc.",
+		"ProductName":     "GPL Ghostscript",
+		"FileDescription": "Ghostscript Interpreter",
+		"ProductVersion":  "9.54.0",
+	}
+
+	loc := file.NewLocation("/usr/bin/gswin64c.exe")
+	p := newPEPackage(vr, loc)
+
+	expected := "pkg:generic/ghostscript@9.54.0"
+	if p.PURL != expected {
+		t.Fatalf("expected purl %q, got %q", expected, p.PURL)
+	}
+}

syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets/elixir/1.19.1/linux-amd64/elixir

@@ -0,0 +1,20 @@
+#!/bin/sh
+
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: 2021 The Elixir Team
+# SPDX-FileCopyrightText: 2012 Plataformatec
+
+set -e
+
+ELIXIR_VERSION=1.19.1
+
+if [ $# -eq 0 ] || { [ $# -eq 1 ] && { [ "$1" = "--help" ] || [ "$1" = "-h" ]; }; }; then
+  cat <<USAGE >&2
+Usage: $(basename "$0") [options] [.exs file] [data]
+
+## General options
+
+  -e "COMMAND"                 Evaluates the given command (*)
+  -h, --help                   Prints this message (standalone)
+  -r "FILE"                    Requires the given files/patterns (*)
+  -S SCRIPT                    Finds and executes the given script in \$PATH

syft/pkg/cataloger/binary/test-fixtures/classifiers/snippets/elixir/1.19.1/linux-amd64/lib/elixir/ebin/elixir.app

@@ -0,0 +1,19 @@
+{application,elixir,
+    [{description,"elixir"},
+     {vsn,"1.19.1"},
+     {modules,
+         ['Elixir.Access','Elixir.Agent.Server','Elixir.Agent',
+          'Elixir.Application','Elixir.ArgumentError',
+          elixir_overridable,elixir_parser,elixir_quote,elixir_rewrite,
+          elixir_sup,elixir_tokenizer,elixir_utils,iex]},
+     {registered,[elixir_sup,elixir_config,elixir_code_server]},
+     {applications,[kernel,stdlib,compiler]},
+     {mod,{elixir,[]}},
+     {env,
+         [{ansi_syntax_colors,
+              [{atom,cyan},
+               {binary,default_color},
+               {operator,default_color}]},
+          {check_endianness,true},
+          {dbg_callback,{'Elixir.Macro',dbg,[]}},
+          {time_zone_database,'Elixir.Calendar.UTCOnlyTimeZoneDatabase'}]}]}.

syft/pkg/cataloger/common/cpe/target_software_to_pkg_type.go

@@ -0,0 +1,58 @@
+package cpe
+
+import (
+	"strings"
+
+	"github.com/anchore/syft/syft/pkg"
+)
+
+// TargetSoftwareToPackageType is derived from looking at target_software attributes in the NVD dataset
+// TODO: ideally this would be driven from the store, where we can resolve ecosystem aliases directly
+func TargetSoftwareToPackageType(tsw string) pkg.Type {
+	tsw = strings.NewReplacer("-", "_", " ", "_").Replace(strings.ToLower(tsw))
+	switch tsw {
+	case "alpine", "apk":
+		return pkg.ApkPkg
+	case "debian", "dpkg":
+		return pkg.DebPkg
+	case "java", "maven", "ant", "gradle", "jenkins", "jenkins_ci", "kafka", "logstash", "mule", "nifi", "solr", "spark", "storm", "struts", "tomcat", "zookeeper", "log4j":
+		return pkg.JavaPkg
+	case "javascript", "node", "nodejs", "node.js", "npm", "yarn", "apache", "jquery", "next.js", "prismjs":
+		return pkg.NpmPkg
+	case "c", "c++", "c/c++", "conan", "gnu_c++", "qt":
+		return pkg.ConanPkg
+	case "dart":
+		return pkg.DartPubPkg
+	case "redhat", "rpm", "redhat_enterprise_linux", "rhel", "suse", "suse_linux", "opensuse", "opensuse_linux", "fedora", "centos", "oracle_linux", "ol":
+		return pkg.RpmPkg
+	case "elixir", "hex":
+		return pkg.HexPkg
+	case "erlang":
+		return pkg.ErlangOTPPkg
+	case ".net", ".net_framework", "asp", "asp.net", "dotnet", "dotnet_framework", "c#", "csharp", "nuget":
+		return pkg.DotnetPkg
+	case "ruby", "gem", "nokogiri", "ruby_on_rails":
+		return pkg.GemPkg
+	case "rust", "cargo", "crates":
+		return pkg.RustPkg
+	case "python", "pip", "pypi", "flask":
+		return pkg.PythonPkg
+	case "kb", "knowledgebase", "msrc", "mskb", "microsoft":
+		return pkg.KbPkg
+	case "portage", "gentoo":
+		return pkg.PortagePkg
+	case "go", "golang", "gomodule":
+		return pkg.GoModulePkg
+	case "linux_kernel", "linux", "z/linux":
+		return pkg.LinuxKernelPkg
+	case "php":
+		return pkg.PhpComposerPkg
+	case "swift":
+		return pkg.SwiftPkg
+	case "wordpress", "wordpress_plugin", "wordpress_":
+		return pkg.WordpressPluginPkg
+	case "lua", "luarocks":
+		return pkg.LuaRocksPkg
+	}
+	return ""
+}

syft/pkg/cataloger/dart/package.go

@@ -1,9 +1,12 @@
 package dart
 
 import (
+	"context"
+
 	"github.com/anchore/packageurl-go"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/pkg"
+	"github.com/anchore/syft/syft/pkg/cataloger/internal/licenses"
 )
 
 func newPubspecLockPackage(name string, raw pubspecLockPackage, locations ...file.Location) pkg.Package {
@@ -29,7 +32,7 @@ func newPubspecLockPackage(name string, raw pubspecLockPackage, locations ...fil
 	return p
 }
 
-func newPubspecPackage(raw pubspecPackage, locations ...file.Location) pkg.Package {
+func newPubspecPackage(ctx context.Context, resolver file.Resolver, raw pubspecPackage, locations ...file.Location) pkg.Package {
 	var env *pkg.DartPubspecEnvironment
 	if raw.Environment.SDK != "" || raw.Environment.Flutter != "" {
 		// this is required only after pubspec v2, but might have been optional before this
@@ -58,6 +61,8 @@ func newPubspecPackage(raw pubspecPackage, locations ...file.Location) pkg.Packa
 
 	p.SetID()
 
+	p = licenses.RelativeToPackage(ctx, resolver, p)
+
 	return p
 }
 

syft/pkg/cataloger/dart/parse_pubspec.go

@@ -29,7 +29,7 @@ type dartPubspecEnvironment struct {
 	Flutter string `mapstructure:"flutter" yaml:"flutter"`
 }
 
-func parsePubspec(_ context.Context, _ file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
+func parsePubspec(ctx context.Context, resolver file.Resolver, _ *generic.Environment, reader file.LocationReadCloser) ([]pkg.Package, []artifact.Relationship, error) {
 	var pkgs []pkg.Package
 
 	dec := yaml.NewDecoder(reader)
@@ -41,6 +41,8 @@ func parsePubspec(_ context.Context, _ file.Resolver, _ *generic.Environment, re
 
 	pkgs = append(pkgs,
 		newPubspecPackage(
+			ctx,
+			resolver,
 			p,
 			reader.WithAnnotation(pkg.EvidenceAnnotationKey, pkg.PrimaryEvidenceAnnotation),
 		),