chore(deps): update anchore dependencies (#4440)

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: willmurphyscode <12529630+willmurphyscode@users.noreply.github.com>

.binny.yaml

@@ -2,7 +2,7 @@ tools:
   # we want to use a pinned version of binny to manage the toolchain (so binny manages itself!)
   - name: binny
     version:
-      want: v0.9.0
+      want: v0.10.0
     method: github-release
     with:
       repo: anchore/binny
@@ -26,7 +26,7 @@ tools:
   # used for linting
   - name: golangci-lint
     version:
-      want: v2.4.0
+      want: v2.7.2
     method: github-release
     with:
       repo: golangci/golangci-lint
@@ -42,7 +42,7 @@ tools:
   # used for signing the checksums file at release
   - name: cosign
     version:
-      want: v2.5.3
+      want: v3.0.2
     method: github-release
     with:
       repo: sigstore/cosign
@@ -58,7 +58,7 @@ tools:
   # used to release all artifacts
   - name: goreleaser
     version:
-      want: v2.11.2
+      want: v2.13.1
     method: github-release
     with:
       repo: goreleaser/goreleaser
@@ -90,7 +90,7 @@ tools:
   # used for running all local and CI tasks
   - name: task
     version:
-      want: v3.44.1
+      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: v2.78.0
+      want: v2.83.1
     method: github-release
     with:
       repo: cli/cli
@@ -106,7 +106,7 @@ tools:
   # used to upload test fixture cache
   - name: oras
     version:
-      want: v1.2.3
+      want: v1.3.0
     method: github-release
     with:
       repo: oras-project/oras
@@ -114,7 +114,7 @@ tools:
   # used to upload test fixture cache
   - name: yq
     version:
-      want: v4.47.1
+      want: v4.49.2
     method: github-release
     with:
       repo: mikefarah/yq

.bouncer.yaml

@@ -9,6 +9,9 @@ permit:
   - Unlicense
 
 ignore-packages:
+  # https://github.com/sorairolake/lzip-go/blob/34a2615d2abf740175c6b0a835baa08364e09430/go.sum.license#L3
+  # has `SPDX-License-Identifier: Apache-2.0 OR MIT`, both of which are acceptable
+  - github.com/sorairolake/lzip-go
   # packageurl-go is released under the MIT license located in the root of the repo at /mit.LICENSE
   - github.com/anchore/packageurl-go
 

.github/actions/bootstrap/action.yaml

@@ -29,7 +29,7 @@ runs:
   using: "composite"
   steps:
     # note: go mod and build is automatically cached on default with v4+
-    - uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # v5.5.0
+    - uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v6.1.0
       if: inputs.go-version != ''
       with:
         go-version: ${{ inputs.go-version }}
@@ -37,7 +37,7 @@ runs:
     - name: Restore tool cache
       if: inputs.tools == 'true'
       id: tool-cache
-      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
+      uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
       with:
         path: ${{ github.workspace }}/.tool
         key: ${{ inputs.cache-key-prefix }}-${{ runner.os }}-tool-${{ hashFiles('.binny.yaml') }}
@@ -63,7 +63,7 @@ runs:
 
     - name: Restore ORAS cache from github actions
       if: inputs.download-test-fixture-cache == 'true'
-      uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809 # v4.2.4
+      uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
       with:
         path: ${{ github.workspace }}/.tmp/oras-cache
         key: ${{ inputs.cache-key-prefix }}-oras-cache

.github/scripts/check_binary_fixture_size.sh

@@ -24,7 +24,7 @@ while IFS= read -r -d '' file; do
     echo "File $file is greater than ${size} bytes."
     found_large_files=1
   fi
-done < <(find "$directory" -type f -print0)
+done < <(git ls-files -z "$directory")
 
 if [ "$found_large_files" -eq 1 ]; then
   echo "Script failed: Some files are greater than ${size} bytes."

.github/workflows/codeql-analysis.yml

@@ -36,18 +36,18 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
       with:
         persist-credentials: false
 
     - name: Install Go
-      uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 #v5.5.0
+      uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c #v6.1.0
       with:
         go-version-file: go.mod
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@3c3833e0f8c1c83d449a7478aa59c036a9165498 #v3.29.5
+      uses: github/codeql-action/init@cf1bb45a277cb3c205638b2cd5c984db1c46a412 #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@3c3833e0f8c1c83d449a7478aa59c036a9165498 #v3.29.5
+      uses: github/codeql-action/autobuild@cf1bb45a277cb3c205638b2cd5c984db1c46a412 #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@3c3833e0f8c1c83d449a7478aa59c036a9165498 #v3.29.5
+      uses: github/codeql-action/analyze@cf1bb45a277cb3c205638b2cd5c984db1c46a412 #v3.29.5

.github/workflows/detect-schema-changes.yaml

@@ -34,7 +34,7 @@ jobs:
       issues: write
     steps:
 
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 

.github/workflows/release.yaml

@@ -9,16 +9,35 @@ on:
       version:
         description: tag the latest commit on main with the given version (prefixed with v)
         required: true
+      phase:
+        description: the specific workflow phase to run or all
+        required: true
+        default: "all"
+        type: choice
+        options:
+          - "all"
+          - "install-script-only"
 
 jobs:
   quality-gate:
     environment: release
     runs-on: ubuntu-24.04
+    if: ${{ github.event.inputs.phase == 'all' }}
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         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:
@@ -110,13 +129,14 @@ jobs:
   release:
     needs: [quality-gate]
     runs-on: ubuntu-24.04
+    if: ${{ github.event.inputs.phase == 'all' }}
     permissions:
       contents: write
       packages: write
       # required for goreleaser signs section with cosign
       id-token: write
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           fetch-depth: 0
           persist-credentials: true
@@ -161,13 +181,13 @@ jobs:
           # for updating brew formula in anchore/homebrew-syft
           GITHUB_BREW_TOKEN: ${{ secrets.ANCHOREOPS_GITHUB_OSS_WRITE_TOKEN }}
 
-      - uses: anchore/sbom-action@da167eac915b4e86f08b264dbdbc867b61be6f0c #v0.20.5
+      - uses: anchore/sbom-action@fbfd9c6c189226748411491745178e0c2017392d #v0.20.10
         continue-on-error: true
         with:
           file: go.mod
           artifact-name: sbom.spdx.json
 
-      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
+      - uses: 8398a7/action-slack@77eaa4f1c608a7d68b38af4e3f739dcd8cba273e #v3.19.0
         continue-on-error: true
         with:
           status: ${{ job.status }}
@@ -179,7 +199,7 @@ jobs:
 
   release-install-script:
     needs: [release]
-    if: ${{ needs.release.result == 'success' }}
+    if: ${{ always() && (needs.release.result == 'success' || github.event.inputs.phase == 'install-script-only') }}
     uses: "anchore/workflows/.github/workflows/release-install-script.yaml@main"
     with:
       tag: ${{ github.event.inputs.version }}

.github/workflows/test-fixture-cache-publish.yaml

@@ -19,7 +19,7 @@ jobs:
     permissions:
       packages: write
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 

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

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository_owner == 'anchore' # only run for main repo (not forks)
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -31,13 +31,13 @@ jobs:
         with:
           repos: ${{ github.event.inputs.repos }}
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@29824e69f54612133e76f7eaac726eef6c875baf #v2.2.1
         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
+      - uses: peter-evans/create-pull-request@22a9089034f40e5a961c8808d113e2c98fb63676 #v7.0.11
         with:
           signoff: true
           delete-branch: true

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

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'anchore/syft' # only run for main repo
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -45,13 +45,13 @@ jobs:
             echo "\`\`\`"
           } >> $GITHUB_STEP_SUMMARY
 
-      - uses: tibdex/github-app-token@3beb63f4bd073e61482598c45c71c1019b59b73a #v2.1.0
+      - uses: actions/create-github-app-token@29824e69f54612133e76f7eaac726eef6c875baf #v2.2.1
         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
+      - uses: peter-evans/create-pull-request@22a9089034f40e5a961c8808d113e2c98fb63676 #v7.0.11
         with:
           signoff: true
           delete-branch: true

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

@@ -14,28 +14,45 @@ 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
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
       - name: Bootstrap environment
         uses: ./.github/actions/bootstrap
+        id: bootstrap
 
-      - name: Bootstrap environment
-        uses: ./.github/actions/bootstrap
+      - name: Login to GitHub Container Registry
+        run: echo "${{ secrets.GITHUB_TOKEN }}" | .tool/oras login ghcr.io -u "$ACTOR" --password-stdin
+        env:
+          ACTOR: ${{ github.actor }}
 
-      - 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@29824e69f54612133e76f7eaac726eef6c875baf #v2.2.1
         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
+      - uses: peter-evans/create-pull-request@22a9089034f40e5a961c8808d113e2c98fb63676 #v7.0.11
         with:
           signoff: true
           delete-branch: true
@@ -47,7 +64,7 @@ jobs:
             Update CPE dictionary index based on the latest available CPE dictionary
           token: ${{ steps.generate-token.outputs.token }}
 
-      - uses: 8398a7/action-slack@1750b5085f3ec60384090fb7c52965ef822e869e #v3.18.0
+      - uses: 8398a7/action-slack@77eaa4f1c608a7d68b38af4e3f739dcd8cba273e #v3.19.0
         with:
           status: ${{ job.status }}
           fields: workflow,eventName,job

.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@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
+        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@22a9089034f40e5a961c8808d113e2c98fb63676 #v7.0.11
+        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/validate-github-actions.yaml

@@ -23,12 +23,12 @@ jobs:
       contents: read
       security-events: write  # for uploading SARIF results
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           persist-credentials: false
 
       - name: "Run zizmor"
-        uses: zizmorcore/zizmor-action@5ca5fc7a4779c5263a3ffa0e1f693009994446d1 # v0.1.2
+        uses: zizmorcore/zizmor-action@e673c3917a1aef3c65c972347ed84ccd013ecda4 # v0.2.0
         with:
           config-file: .github/zizmor.yml
           sarif-upload: true

.github/workflows/validations.yaml

@@ -17,7 +17,7 @@ jobs:
     name: "Static analysis"
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -34,7 +34,7 @@ jobs:
     # we need more storage than what's on the default runner
     runs-on: ubuntu-22.04-4core-16gb
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -52,7 +52,7 @@ jobs:
     name: "Integration tests"
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -72,7 +72,7 @@ jobs:
     name: "Build snapshot artifacts"
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -90,7 +90,7 @@ jobs:
       # why not use actions/upload-artifact? It is very slow (3 minutes to upload ~600MB of data, vs 10 seconds with this approach).
       # see https://github.com/actions/upload-artifact/issues/199 for more info
       - name: Upload snapshot artifacts
-        uses: actions/cache/save@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/cache/save@0057852bfaa89a56745cba8c7296529d2fc39830 #v4.3.0
         with:
           # we need to preserve the snapshot data itself as well as the task data that confirms if the
           # snapshot build is stale or not. Otherwise the downstream jobs will attempt to rebuild the snapshot
@@ -107,7 +107,7 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -118,7 +118,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 #v4.3.0
         with:
           path: |
             snapshot
@@ -133,7 +133,7 @@ jobs:
 
       - run: npm install @actions/artifact@2.2.2
 
-      - uses: actions/github-script@v7
+      - uses: actions/github-script@v8
         with:
           script: |
             const { readdirSync } = require('fs')
@@ -164,7 +164,7 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -175,7 +175,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 #v4.3.0
         with:
           path: |
             snapshot
@@ -210,9 +210,9 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Install Cosign
-        uses: sigstore/cosign-installer@d58896d6a1865668819e1d91763c7751a165e159 # v3.9.2
+        uses: sigstore/cosign-installer@faadad0cce49287aee09b3a48701e75088a2c6ad # v4.0.0
 
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -225,7 +225,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 #v4.3.0
         with:
           path: |
             snapshot
@@ -251,7 +251,7 @@ jobs:
     needs: [Build-Snapshot-Artifacts]
     runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 
@@ -262,7 +262,7 @@ jobs:
 
       - name: Download snapshot build
         id: snapshot-cache
-        uses: actions/cache/restore@0400d5f644dc74513175e3cd8d07132dd4860809 #v4.2.4
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 #v4.3.0
         with:
           path: |
             snapshot
@@ -291,7 +291,7 @@ jobs:
       - Cli-Linux
       - Upload-Snapshot-Artifacts
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 #v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
         with:
           persist-credentials: false
 

.gitignore

@@ -2,6 +2,7 @@
 go.work
 go.work.sum
 .tool-versions
+.python-version
 
 # app configuration
 /.syft.yaml
@@ -16,6 +17,8 @@ bin/
 /snapshot
 /.tool
 /.task
+/generate
+/specs
 
 # changelog generation
 CHANGELOG.md
@@ -70,3 +73,5 @@ cosign.pub
 __pycache__/
 *.py[cod]
 *$py.class
+
+

.golangci.yaml

@@ -49,6 +49,12 @@ linters:
       - common-false-positives
       - legacy
       - std-error-handling
+    rules:
+      # internal/os contains OS feature detection logic; the name reflects its purpose
+      - linters:
+          - revive
+        path: internal/os/
+        text: "var-naming: avoid package names that conflict"
     paths:
       - third_party$
       - builtin$

.goreleaser.yaml

@@ -42,7 +42,7 @@ builds:
     dir: ./cmd/syft
     binary: syft
     goos: [windows]
-    goarch: [amd64]
+    goarch: [amd64, arm64]
     mod_timestamp: *build-timestamp
     ldflags: *build-ldflags
 
@@ -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}"

DEVELOPING.md

@@ -27,7 +27,7 @@ Also double check that the docker context being used is the default context. If
 
 `docker context use default`
 
-After cloning the following step can help you get setup:
+After cloning, the following steps can help you get setup:
 1. run `make bootstrap` to download go mod dependencies, create the `/.tmp` dir, and download helper utilities.
 2. run `make` to view the selection of developer commands in the Makefile
 3. run `make build` to build the release snapshot binaries and packages
@@ -120,7 +120,7 @@ sequenceDiagram
     source-->>+sbom: add source to SBOM struct
     source-->>+catalog: pass src to generate catalog
     catalog-->-sbom: add cataloging results onto SBOM
-    sbom-->>encoder: pass SBOM and format desiered to syft encoder
+    sbom-->>encoder: pass SBOM and format desired to syft encoder
     encoder-->>source: return bytes that are the SBOM of the original input 
 
     Note right of catalog: cataloger configuration is done based on src
@@ -186,7 +186,7 @@ Cataloger names should be unique and named with the following rules of thumb in
 - Use lowercase letters, numbers, and hyphens only
 - Use hyphens to separate words
 - Catalogers for language ecosystems should start with the language name (e.g. `python-` for a cataloger that raises up python packages)
-- Distinct between when the cataloger is searching for evidence of installed packages vs declared packages. For example, there are currently two different gemspec-based catalogers, the `ruby-gemspec-cataloger` and `ruby-installed-gemspec-cataloger`, where the latter requires that the gemspec is found within a `specifications` directory (which means it was installed, not just at the root of a source repo).
+- Distinguish between when the cataloger is searching for evidence of installed packages vs declared packages. For example, there are currently two different gemspec-based catalogers, the `ruby-gemspec-cataloger` and `ruby-installed-gemspec-cataloger`, where the latter requires that the gemspec is found within a `specifications` directory (which means it was installed, not just at the root of a source repo).
 
 #### Building a new Cataloger
 

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.
 
@@ -133,8 +133,9 @@ Note that flags using the @<version> can be used for earlier versions of each sp
 - Elixir (mix)
 - Erlang (rebar3)
 - 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)

SECURITY.md

@@ -29,4 +29,4 @@ To report a security issue, please email
 with a description of the issue, the steps you took to create the issue,
 affected versions, and, if known, mitigations for the issue.
 
-All support will be made on the best effort base, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.
+All support will be made on a best effort basis, so please indicate the "urgency level" of the vulnerability as Critical, High, Medium or Low.

Taskfile.yaml

@@ -1,5 +1,9 @@
 
 version: "3"
+
+includes:
+  generate:cpe-index: ./task.d/generate/cpe-index.yaml
+
 vars:
   OWNER: anchore
   PROJECT: syft
@@ -502,7 +506,7 @@ tasks:
   generate-json-schema:
     desc: Generate a new JSON schema
     cmds:
-      - "cd syft/internal && go generate . && cd jsonschema && go run . && go fmt ../..."
+      - "cd ./internal && go generate . && cd ./jsonschema && go run . && go fmt ../..."
 
   generate-license-list:
     desc: Generate an updated license processing code off of the latest available SPDX license list
@@ -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

@@ -4,18 +4,17 @@ go 1.24.1
 
 require (
 	github.com/BurntSushi/toml v1.5.0
-	github.com/CycloneDX/cyclonedx-go v0.9.2
+	github.com/CycloneDX/cyclonedx-go v0.9.3
 	github.com/Masterminds/semver/v3 v3.4.0
 	github.com/Masterminds/sprig/v3 v3.3.0
 	github.com/OneOfOne/xxhash v1.2.8
 	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
@@ -24,14 +23,14 @@ 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 v0.1.9-0.20250826202322-ef061ea78385
+	github.com/anchore/stereoscope v0.1.14
 	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
 	github.com/blakesmith/ar v0.0.0-20190502131153-809d4375e1fb
 	github.com/bmatcuk/doublestar/v4 v4.9.1
 	github.com/charmbracelet/bubbles v0.21.0
-	github.com/charmbracelet/bubbletea v1.3.6
+	github.com/charmbracelet/bubbletea v1.3.10
 	github.com/charmbracelet/lipgloss v1.1.0
 	github.com/dave/jennifer v1.7.1
 	github.com/deitch/magic v0.0.0-20230404182410-1ff89d7342da
@@ -40,35 +39,35 @@ 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/gkampitakis/go-snaps v0.5.14
-	github.com/go-git/go-billy/v5 v5.6.2
-	github.com/go-git/go-git/v5 v5.16.2
+	github.com/github/go-spdx/v2 v2.3.5
+	github.com/gkampitakis/go-snaps v0.5.18
+	github.com/go-git/go-billy/v5 v5.7.0
+	github.com/go-git/go-git/v5 v5.16.3
 	github.com/go-test/deep v1.1.1
 	github.com/go-viper/mapstructure/v2 v2.4.0
-	github.com/gohugoio/hashstructure v0.5.0
+	github.com/gohugoio/hashstructure v0.6.0
 	github.com/google/go-cmp v0.7.0
-	github.com/google/go-containerregistry v0.20.6
+	github.com/google/go-containerregistry v0.20.7
 	github.com/google/licensecheck v0.3.1
 	github.com/google/uuid v1.6.0
-	github.com/gookit/color v1.5.4
+	github.com/gookit/color v1.6.0
 	github.com/hashicorp/go-cleanhttp v0.5.2
-	github.com/hashicorp/go-getter v1.7.9
+	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 v6.7.5
 	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 v0.1.3
+	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 v1.1.2
 	github.com/opencontainers/go-digest v1.0.0
 	github.com/pelletier/go-toml v1.9.5
-	github.com/quasilyte/go-ruleguard/dsl v0.3.22
+	github.com/quasilyte/go-ruleguard/dsl v0.3.23
 	github.com/rust-secure-code/go-rustaudit v0.0.0-20250226111315-e20ec32e963c
 	github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d
 	github.com/sanity-io/litter v1.5.8
@@ -78,10 +77,10 @@ require (
 	github.com/sergi/go-diff v1.4.0
 	github.com/spdx/gordf v0.0.0-20201111095634-7098f93598fb
 	github.com/spdx/tools-golang v0.5.5
-	github.com/spf13/afero v1.14.0
-	github.com/spf13/cobra v1.9.1
-	github.com/stretchr/testify v1.11.0
-	github.com/vbatts/go-mtree v0.5.4
+	github.com/spf13/afero v1.15.0
+	github.com/spf13/cobra v1.10.2
+	github.com/stretchr/testify v1.11.1
+	github.com/vbatts/go-mtree v0.6.0
 	github.com/vifraa/gopom v1.0.0
 	github.com/wagoodman/go-partybus v0.0.0-20230516145632-8ccac152c651
 	github.com/wagoodman/go-progress v0.0.0-20230925121702-07e42b3cdba0
@@ -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 v0.27.0
-	golang.org/x/net v0.43.0
-	modernc.org/sqlite v1.38.2
+	golang.org/x/mod v0.31.0
+	golang.org/x/net v0.48.0
+	modernc.org/sqlite v1.40.1
 )
 
 require (
@@ -109,30 +108,29 @@ require (
 	github.com/Masterminds/goutils v1.1.1 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/Microsoft/hcsshim v0.11.7 // indirect
-	github.com/ProtonMail/go-crypto v1.2.0 // indirect
-	github.com/STARRY-S/zip v0.2.1 // indirect
+	github.com/ProtonMail/go-crypto v1.3.0 // indirect
+	github.com/STARRY-S/zip v0.2.3 // indirect
 	github.com/agext/levenshtein v1.2.1 // indirect; indirectt
 	github.com/anchore/go-lzo v0.1.0 // indirect
 	github.com/anchore/go-struct-converter v0.0.0-20221118182256-c68fdcfa2092 // indirect
-	github.com/andybalholm/brotli v1.1.2-0.20250424173009-453214e765f3 // indirect
+	github.com/andybalholm/brotli v1.2.0 // indirect
 	github.com/apparentlymart/go-textseg/v15 v15.0.0 // indirect
 	github.com/aquasecurity/go-version v0.0.1 // indirect
 	github.com/atotto/clipboard v0.1.4 // indirect
-	github.com/aws/aws-sdk-go v1.44.122 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/becheran/wildmatch-go v1.0.0 // indirect
 	github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d // indirect
 	github.com/bodgit/plumbing v1.3.0 // indirect
-	github.com/bodgit/sevenzip v1.6.0 // indirect
+	github.com/bodgit/sevenzip v1.6.1 // indirect
 	github.com/bodgit/windows v1.0.1 // indirect
 	github.com/charmbracelet/colorprofile v0.2.3-0.20250311203215-f60798e515dc // indirect
 	github.com/charmbracelet/harmonica v0.2.0 // indirect
-	github.com/charmbracelet/x/ansi v0.9.3 // indirect
+	github.com/charmbracelet/x/ansi v0.10.1 // indirect
 	github.com/charmbracelet/x/cellbuf v0.0.13-0.20250311204145-2c3ea96c31dd // indirect
 	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
@@ -140,64 +138,60 @@ require (
 	github.com/containerd/fifo v1.1.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
 	github.com/containerd/platforms v0.2.1 // indirect
-	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
+	github.com/containerd/stargz-snapshotter/estargz v0.18.1 // 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 v28.3.2+incompatible // indirect
+	github.com/docker/cli v29.1.2+incompatible // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
-	github.com/docker/docker v28.3.3+incompatible // indirect
-	github.com/docker/docker-credential-helpers v0.9.3 // indirect
+	github.com/docker/docker v28.5.2+incompatible // indirect
+	github.com/docker/docker-credential-helpers v0.9.4 // indirect
 	github.com/docker/go-connections v0.6.0 // indirect
 	github.com/docker/go-events v0.0.0-20190806004212-e31b211e4f1c // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/dsnet/compress v0.0.2-0.20230904184137-39efe44ab707 // indirect
 	github.com/emirpasic/gods v1.18.1 // indirect
 	github.com/erikgeiser/coninput v0.0.0-20211004153227-1c3628e74d0f // indirect
-	github.com/fatih/color v1.17.0 // indirect
+	github.com/fatih/color v1.18.0 // indirect
 	github.com/felixge/fgprof v0.9.5 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fsnotify/fsnotify v1.8.0 // indirect
-	github.com/gabriel-vasile/mimetype v1.4.9 // indirect
+	github.com/gabriel-vasile/mimetype v1.4.11 // indirect
 	github.com/gkampitakis/ciinfo v0.3.2 // indirect
-	github.com/gkampitakis/go-diff v1.3.2 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-restruct/restruct v1.2.0-alpha // indirect
-	github.com/goccy/go-yaml v1.18.0
+	github.com/goccy/go-yaml v1.19.0
 	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
 	github.com/googleapis/gax-go/v2 v2.13.0 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/hashicorp/go-safetemp v1.0.0 // indirect
 	github.com/hashicorp/go-version v1.6.0 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
 	github.com/huandu/xstrings v1.5.0 // indirect
-	github.com/iancoleman/orderedmap v0.0.0-20190318233801-ac98e3ecb4b0 // indirect
+	github.com/iancoleman/orderedmap v0.3.0
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
-	github.com/jmespath/go-jmespath v0.4.0 // indirect
 	github.com/kevinburke/ssh_config v1.2.0 // indirect
-	github.com/klauspost/compress v1.18.0 // indirect
+	github.com/klauspost/compress v1.18.1 // indirect
 	github.com/klauspost/pgzip v1.2.6 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/logrusorgru/aurora v2.0.3+incompatible // indirect
 	github.com/lucasb-eyer/go-colorful v1.2.0 // indirect
 	github.com/maruel/natural v1.1.1 // indirect
-	github.com/mattn/go-colorable v0.1.13 // indirect
+	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 v1.0.0 // indirect
+	github.com/minio/minlz v1.0.1 // indirect
 	github.com/mitchellh/copystructure v1.2.0 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/mitchellh/go-wordwrap v1.0.1 // indirect
@@ -212,13 +206,9 @@ 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 v2.1.0 // 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
@@ -235,22 +225,22 @@ require (
 	github.com/shopspring/decimal v1.4.0 // indirect
 	github.com/sirupsen/logrus v1.9.4-0.20230606125235-dd1b4c2e81af // indirect
 	github.com/skeema/knownhosts v1.3.1 // indirect
-	github.com/sorairolake/lzip-go v0.3.5 // indirect
+	github.com/sorairolake/lzip-go v0.3.8 // indirect
 	github.com/sourcegraph/conc v0.3.0 // indirect
 	github.com/spf13/cast v1.7.1 // indirect
-	github.com/spf13/pflag v1.0.6 // indirect
+	github.com/spf13/pflag v1.0.9 // indirect
 	github.com/spf13/viper v1.20.0 // indirect
 	github.com/stretchr/objx v0.5.2 // indirect
 	github.com/subosito/gotenv v1.6.0 // indirect
-	github.com/sylabs/sif/v2 v2.21.1 // indirect
+	github.com/sylabs/sif/v2 v2.22.0 // indirect
 	github.com/sylabs/squashfs v1.0.6 // indirect
 	github.com/therootcompany/xz v1.0.1 // indirect
 	github.com/tidwall/gjson v1.18.0 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tidwall/sjson v1.2.5 // indirect
-	github.com/ulikunitz/xz v0.5.12 // indirect
-	github.com/vbatts/tar-split v0.12.1 // indirect
+	github.com/ulikunitz/xz v0.5.15 // indirect
+	github.com/vbatts/tar-split v0.12.2 // indirect
 	github.com/xanzy/ssh-agent v0.3.3 // indirect
 	github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb // indirect
 	github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 // indirect
@@ -267,28 +257,69 @@ require (
 	go.uber.org/atomic v1.9.0 // indirect
 	go.uber.org/multierr v1.9.0 // indirect
 	go4.org v0.0.0-20230225012048-214862532bf5 // indirect
-	golang.org/x/crypto v0.41.0 // indirect
-	golang.org/x/oauth2 v0.30.0 // indirect
-	golang.org/x/sync v0.16.0 // indirect
-	golang.org/x/sys v0.35.0 // indirect
-	golang.org/x/term v0.34.0 // indirect
-	golang.org/x/text v0.28.0 // indirect
-	golang.org/x/time v0.12.0 // indirect
-	golang.org/x/tools v0.35.0
+	golang.org/x/crypto v0.46.0 // indirect
+	golang.org/x/oauth2 v0.33.0 // indirect
+	golang.org/x/sync v0.19.0 // indirect
+	golang.org/x/sys v0.39.0 // indirect
+	golang.org/x/term v0.38.0 // indirect
+	golang.org/x/text v0.32.0 // indirect
+	golang.org/x/time v0.14.0
+	golang.org/x/tools v0.40.0
 	golang.org/x/xerrors v0.0.0-20231012003039-104605ab7028 // indirect
 	google.golang.org/api v0.203.0 // indirect
 	google.golang.org/genproto v0.0.0-20241118233622-e639e219e697 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20241113202542-65e8d215514f // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20241223144023-3abc09e42ca8 // indirect
 	google.golang.org/grpc v1.67.3 // indirect
-	google.golang.org/protobuf v1.36.4 // indirect
+	google.golang.org/protobuf v1.36.6 // indirect
 	gopkg.in/warnings.v0 v0.1.2 // indirect
-	gopkg.in/yaml.v3 v3.0.1 // indirect
-	modernc.org/libc v1.66.3 // indirect
+	gopkg.in/yaml.v3 v3.0.1
+	modernc.org/libc v1.66.10 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect
 )
 
+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 v1.39.6 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.10 // indirect
+	github.com/aws/aws-sdk-go-v2/config v1.31.17 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.18.21 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.13 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.13 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.13 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.3.34 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.3 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.7.2 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.15 // indirect
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.80.1 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.1 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.5 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.39.1 // indirect
+	github.com/aws/smithy-go v1.23.2 // indirect
+	github.com/clipperhouse/displaywidth v0.6.0 // indirect
+	github.com/clipperhouse/stringish v0.1.1 // indirect
+	github.com/clipperhouse/uax29/v2 v2.3.0 // 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 v0.1.3 // indirect
+	github.com/smallnest/ringbuffer v0.0.0-20241116012123-461381446e3d // indirect
+	gonum.org/v1/gonum v0.15.1 // indirect
+)
+
 retract (
 	v1.25.0 // published with a replace directive (confusing for API users)
 	v0.53.2

internal/cache/README.md

@@ -18,7 +18,7 @@ based on the _structure_ of the provided type.
 If the structure changes in any way it will end up with a new version key and all will re populate this new key,
 ignoring cached values from older, different versions.
 The resolver will store items using the `json` package to serialize/deserialize values, so to save space
-it is encouraged  to use `omitempty`. For example:
+it is encouraged to use `omitempty`. For example:
 
 ```go
 type myCacheItem struct {

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 = "16.0.39"
+	JSONSchemaVersion = "16.1.0"
+
+	// Changelog
+	// 16.1.0 - reformulated the python pdm fields (added "URL" and removed the unused "path" field).
+
 )

internal/file/archive_aliases.go

@@ -0,0 +1,46 @@
+package file
+
+import (
+	"context"
+	"io"
+	"path/filepath"
+	"strings"
+
+	"github.com/mholt/archives"
+)
+
+// compoundExtensionAliases maps shorthand archive extensions to their full forms.
+// The mholt/archives library doesn't recognize these aliases natively.
+//
+// See: https://github.com/anchore/syft/issues/4416
+// Reference: https://github.com/mholt/archives?tab=readme-ov-file#supported-compression-formats
+var compoundExtensionAliases = map[string]string{
+	".tgz":  ".tar.gz",
+	".tbz2": ".tar.bz2",
+	".txz":  ".tar.xz",
+	".tlz":  ".tar.lz",
+	".tzst": ".tar.zst",
+}
+
+// IdentifyArchive is a wrapper around archives.Identify that handles compound extension
+// aliases (like .tgz -> .tar.gz) transparently. It first attempts filename-based detection
+// using the alias map, and falls back to content-based detection if needed.
+//
+// This function is a drop-in replacement for archives.Identify that centralizes
+// the compound alias handling logic in one place.
+func IdentifyArchive(ctx context.Context, path string, r io.Reader) (archives.Format, io.Reader, error) {
+	// First, try to identify using the alias-mapped path (filename-based detection)
+	normalizedPath := handleCompoundArchiveAliases(path)
+	return archives.Identify(ctx, normalizedPath, r)
+}
+
+// handleCompoundArchiveAliases normalizes archive file paths that use compound extension
+// aliases (like .tgz) to their full forms (like .tar.gz) for correct identification
+// by the mholt/archives library.
+func handleCompoundArchiveAliases(path string) string {
+	ext := filepath.Ext(path)
+	if newExt, ok := compoundExtensionAliases[ext]; ok {
+		return strings.TrimSuffix(path, ext) + newExt
+	}
+	return path
+}

internal/file/archive_aliases_test.go

@@ -0,0 +1,73 @@
+package file
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestHandleCompoundArchiveAliases(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected string
+	}{
+		{
+			name:     "tgz to tar.gz",
+			input:    "/path/to/archive.tgz",
+			expected: "/path/to/archive.tar.gz",
+		},
+		{
+			name:     "tbz2 to tar.bz2",
+			input:    "/path/to/archive.tbz2",
+			expected: "/path/to/archive.tar.bz2",
+		},
+		{
+			name:     "txz to tar.xz",
+			input:    "/path/to/archive.txz",
+			expected: "/path/to/archive.tar.xz",
+		},
+		{
+			name:     "tlz to tar.lz",
+			input:    "/path/to/archive.tlz",
+			expected: "/path/to/archive.tar.lz",
+		},
+		{
+			name:     "tzst to tar.zst",
+			input:    "/path/to/archive.tzst",
+			expected: "/path/to/archive.tar.zst",
+		},
+		{
+			name:     "standard tar.gz unchanged",
+			input:    "/path/to/archive.tar.gz",
+			expected: "/path/to/archive.tar.gz",
+		},
+		{
+			name:     "zip unchanged",
+			input:    "/path/to/archive.zip",
+			expected: "/path/to/archive.zip",
+		},
+		{
+			name:     "no extension unchanged",
+			input:    "/path/to/archive",
+			expected: "/path/to/archive",
+		},
+		{
+			name:     "case sensitive - TGZ not matched",
+			input:    "/path/to/archive.TGZ",
+			expected: "/path/to/archive.TGZ",
+		},
+		{
+			name:     "just filename with tgz",
+			input:    "archive.tgz",
+			expected: "archive.tar.gz",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := handleCompoundArchiveAliases(tt.input)
+			assert.Equal(t, tt.expected, result)
+		})
+	}
+}

internal/file/glob_match.go

@@ -1,46 +0,0 @@
-package file
-
-// GlobMatch evaluates the given glob pattern against the given "name" string, indicating if there is a match or not.
-// Source: https://research.swtch.com/glob.go
-func GlobMatch(pattern, name string) bool {
-	px := 0
-	nx := 0
-	nextPx := 0
-	nextNx := 0
-	for px < len(pattern) || nx < len(name) {
-		if px < len(pattern) {
-			c := pattern[px]
-			switch c {
-			default: // ordinary character
-				if nx < len(name) && name[nx] == c {
-					px++
-					nx++
-					continue
-				}
-			case '?': // single-character wildcard
-				if nx < len(name) {
-					px++
-					nx++
-					continue
-				}
-			case '*': // zero-or-more-character wildcard
-				// Try to match at nx.
-				// If that doesn't work out,
-				// restart at nx+1 next.
-				nextPx = px
-				nextNx = nx + 1
-				px++
-				continue
-			}
-		}
-		// Mismatch. Maybe restart.
-		if 0 < nextNx && nextNx <= len(name) {
-			px = nextPx
-			nx = nextNx
-			continue
-		}
-		return false
-	}
-	// Matched all of pattern to all of name. Success.
-	return true
-}

internal/file/glob_match_test.go

@@ -1,39 +0,0 @@
-package file
-
-import (
-	"strings"
-	"testing"
-)
-
-func TestGlobMatch(t *testing.T) {
-	var tests = []struct {
-		pattern string
-		data    string
-		ok      bool
-	}{
-		{"", "", true},
-		{"x", "", false},
-		{"", "x", false},
-		{"abc", "abc", true},
-		{"*", "abc", true},
-		{"*c", "abc", true},
-		{"*b", "abc", false},
-		{"a*", "abc", true},
-		{"b*", "abc", false},
-		{"a*", "a", true},
-		{"*a", "a", true},
-		{"a*b*c*d*e*", "axbxcxdxe", true},
-		{"a*b*c*d*e*", "axbxcxdxexxx", true},
-		{"a*b?c*x", "abxbbxdbxebxczzx", true},
-		{"a*b?c*x", "abxbbxdbxebxczzy", false},
-		{"a*a*a*a*b", strings.Repeat("a", 100), false},
-		{"*x", "xxx", true},
-		{"/home/place/**", "/home/place/a/thing", true},
-	}
-
-	for _, test := range tests {
-		if GlobMatch(test.pattern, test.data) != test.ok {
-			t.Errorf("failed glob='%s' data='%s'", test.pattern, test.data)
-		}
-	}
-}

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 := IdentifyArchive(ctx, archivePath, tarReader)
+	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/test-fixtures/zip-source/b-file/in-subdir.txt

@@ -0,0 +1 @@
+this file is in a subdirectory

internal/file/zip_file_helpers_test.go

@@ -7,14 +7,14 @@ import (
 	"path/filepath"
 	"syscall"
 	"testing"
-
-	"github.com/stretchr/testify/assert"
 )
 
 var expectedZipArchiveEntries = []string{
-	"some-dir" + string(os.PathSeparator),
-	filepath.Join("some-dir", "a-file.txt"),
+	"some-dir/",
+	"some-dir/a-file.txt",
 	"b-file.txt",
+	"b-file/",
+	"b-file/in-subdir.txt",
 	"nested.zip",
 }
 
@@ -59,12 +59,6 @@ func createZipArchive(t testing.TB, sourceDirPath, destinationArchivePath string
 
 }
 
-func assertNoError(t testing.TB, fn func() error) func() {
-	return func() {
-		assert.NoError(t, fn())
-	}
-}
-
 // setupZipFileTest encapsulates common test setup work for zip file tests. It returns a cleanup function,
 // which should be called (typically deferred) by the caller, the path of the created zip archive, and an error,
 // which should trigger a fatal test failure in the consuming test. The returned cleanup function will never be nil

internal/file/zip_file_manifest.go

@@ -1,10 +1,13 @@
 package file
 
 import (
+	"context"
 	"os"
 	"sort"
 	"strings"
 
+	"github.com/bmatcuk/doublestar/v4"
+	"github.com/mholt/archives"
 	"github.com/scylladb/go-set/strset"
 
 	"github.com/anchore/syft/internal/log"
@@ -14,22 +17,25 @@ 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
 }
@@ -39,12 +45,17 @@ func (z ZipFileManifest) Add(entry string, info os.FileInfo) {
 	z[entry] = info
 }
 
-// GlobMatch returns the path keys that match the given value(s).
+// GlobMatch returns the path keys to files (not directories) that match the given value(s).
 func (z ZipFileManifest) GlobMatch(caseInsensitive bool, patterns ...string) []string {
 	uniqueMatches := strset.New()
 
 	for _, pattern := range patterns {
 		for entry := range z {
+			fileInfo := z[entry]
+			if fileInfo != nil && fileInfo.IsDir() {
+				continue
+			}
+
 			// We want to match globs as if entries begin with a leading slash (akin to an absolute path)
 			// so that glob logic is consistent inside and outside of ZIP archives
 			normalizedEntry := normalizeZipEntryName(caseInsensitive, entry)
@@ -52,7 +63,13 @@ func (z ZipFileManifest) GlobMatch(caseInsensitive bool, patterns ...string) []s
 			if caseInsensitive {
 				pattern = strings.ToLower(pattern)
 			}
-			if GlobMatch(pattern, normalizedEntry) {
+
+			matches, err := doublestar.Match(pattern, normalizedEntry)
+			if err != nil {
+				log.Debugf("error with match pattern '%s', including by default: %v", pattern, err)
+				matches = true
+			}
+			if matches {
 				uniqueMatches.Add(entry)
 			}
 		}

internal/file/zip_file_manifest_test.go

@@ -4,10 +4,13 @@
 package file
 
 import (
+	"context"
 	"encoding/json"
 	"os"
 	"path"
 	"testing"
+
+	"github.com/stretchr/testify/require"
 )
 
 func TestNewZipFileManifest(t *testing.T) {
@@ -24,7 +27,7 @@ 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 +62,7 @@ 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)
 	}
@@ -99,30 +102,34 @@ 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)
 	}
 
 	cases := []struct {
 		glob     string
-		expected string
+		expected []string
 	}{
 		{
 			"/b*",
-			"b-file.txt",
+			[]string{"b-file.txt"},
 		},
 		{
-			"*/a-file.txt",
-			"some-dir/a-file.txt",
+			"/b*/**",
+			[]string{"b-file.txt", "b-file/in-subdir.txt"},
 		},
 		{
-			"*/A-file.txt",
-			"some-dir/a-file.txt",
+			"**/a-file.txt",
+			[]string{"some-dir/a-file.txt"},
+		},
+		{
+			"**/A-file.txt",
+			[]string{"some-dir/a-file.txt"},
 		},
 		{
 			"**/*.zip",
-			"nested.zip",
+			[]string{"nested.zip"},
 		},
 	}
 
@@ -132,11 +139,7 @@ func TestZipFileManifest_GlobMatch(t *testing.T) {
 
 			results := z.GlobMatch(true, glob)
 
-			if len(results) == 1 && results[0] == tc.expected {
-				return
-			}
-
-			t.Errorf("unexpected results for glob '%s': %+v", glob, results)
+			require.ElementsMatch(t, tc.expected, results)
 		})
 	}
 }

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/jsonschema/README.md

@@ -0,0 +1 @@
+Please see [schema/json/README.md](../../schema/json/README.md) for more information on the JSON schema files in this directory.

internal/jsonschema/comments.go

@@ -0,0 +1,159 @@
+package main
+
+import (
+	"fmt"
+	"go/ast"
+	"go/parser"
+	"go/token"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"github.com/invopop/jsonschema"
+)
+
+func copyAliasFieldComments(commentMap map[string]string, repoRoot string) {
+	// find all type aliases by parsing Go source files
+	aliases := findTypeAliases(repoRoot)
+
+	// for each alias, copy field comments from the source type
+	for aliasName, sourceName := range aliases {
+		// find all field comments for the source type
+		for key, comment := range commentMap {
+			// check if this is a field comment for the source type
+			// format: "github.com/anchore/syft/syft/pkg.SourceType.FieldName"
+			if strings.Contains(key, "."+sourceName+".") {
+				// create the corresponding key for the alias
+				aliasKey := strings.Replace(key, "."+sourceName+".", "."+aliasName+".", 1)
+				commentMap[aliasKey] = comment
+			}
+		}
+	}
+}
+
+func findTypeAliases(repoRoot string) map[string]string {
+	aliases := make(map[string]string)
+	fset := token.NewFileSet()
+
+	// walk through all Go files in the repo
+	err := filepath.Walk(repoRoot, func(path string, info os.FileInfo, err error) error {
+		if err != nil || info.IsDir() || !strings.HasSuffix(path, ".go") {
+			return nil
+		}
+
+		// parse the file
+		file, err := parser.ParseFile(fset, path, nil, parser.ParseComments)
+		if err != nil {
+			return nil
+		}
+
+		// look for type alias declarations
+		ast.Inspect(file, func(n ast.Node) bool {
+			typeSpec, ok := n.(*ast.TypeSpec)
+			if !ok {
+				return true
+			}
+
+			// check if this is a type alias (e.g., type A B where B is an identifier)
+			ident, ok := typeSpec.Type.(*ast.Ident)
+			if !ok {
+				return true
+			}
+
+			// store the alias mapping: aliasName -> sourceName
+			aliases[typeSpec.Name.Name] = ident.Name
+			return true
+		})
+
+		return nil
+	})
+
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "error: failed to find type aliases: %v\n", err)
+		panic(err)
+	}
+
+	return aliases
+}
+
+func hasDescriptionInAlternatives(schema *jsonschema.Schema) bool {
+	// check oneOf alternatives
+	for _, alt := range schema.OneOf {
+		if alt.Description != "" {
+			return true
+		}
+	}
+	// check anyOf alternatives
+	for _, alt := range schema.AnyOf {
+		if alt.Description != "" {
+			return true
+		}
+	}
+	return false
+}
+
+func warnMissingDescriptions(schema *jsonschema.Schema, metadataNames []string) { //nolint:gocognit
+	var missingTypeDescriptions []string
+	var missingFieldDescriptions []string
+
+	// check metadata types for missing descriptions
+	for _, name := range metadataNames {
+		def, ok := schema.Definitions[name]
+		if !ok {
+			continue
+		}
+
+		// check if type has a description
+		if def.Description == "" {
+			missingTypeDescriptions = append(missingTypeDescriptions, name)
+		}
+
+		// check if fields have descriptions
+		if def.Properties != nil {
+			for _, fieldName := range def.Properties.Keys() {
+				fieldSchemaRaw, _ := def.Properties.Get(fieldName)
+				fieldSchema, ok := fieldSchemaRaw.(*jsonschema.Schema)
+				if !ok {
+					continue
+				}
+
+				// skip if field has a description
+				if fieldSchema.Description != "" {
+					continue
+				}
+
+				// skip if field is a reference (descriptions come from the referenced type)
+				if fieldSchema.Ref != "" {
+					continue
+				}
+
+				// skip if field is an array/object with items that are references
+				if fieldSchema.Items != nil && fieldSchema.Items.Ref != "" {
+					continue
+				}
+
+				// skip if field uses oneOf/anyOf with descriptions in the alternatives
+				if hasDescriptionInAlternatives(fieldSchema) {
+					continue
+				}
+
+				missingFieldDescriptions = append(missingFieldDescriptions, fmt.Sprintf("%s.%s", name, fieldName))
+			}
+		}
+	}
+
+	// report findings
+	if len(missingTypeDescriptions) > 0 {
+		fmt.Fprintf(os.Stderr, "\nwarning: %d metadata types are missing descriptions:\n", len(missingTypeDescriptions))
+		for _, name := range missingTypeDescriptions {
+			fmt.Fprintf(os.Stderr, "  - %s\n", name)
+		}
+	}
+
+	if len(missingFieldDescriptions) > 0 {
+		fmt.Fprintf(os.Stderr, "\nwarning: %d fields are missing descriptions:\n", len(missingFieldDescriptions))
+		for _, field := range missingFieldDescriptions {
+			fmt.Fprintf(os.Stderr, "  - %s\n", field)
+		}
+	}
+}

internal/jsonschema/comments_test.go

@@ -0,0 +1,382 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/iancoleman/orderedmap"
+	"github.com/invopop/jsonschema"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestCopyAliasFieldComments verifies that field comments from source types are correctly copied to alias types.
+// This is important for type aliases like `type RpmArchive RpmDBEntry` where the alias should inherit all field descriptions.
+func TestCopyAliasFieldComments(t *testing.T) {
+	tests := []struct {
+		name         string
+		commentMap   map[string]string
+		aliases      map[string]string
+		wantComments map[string]string
+	}{
+		{
+			name: "copies field comments from source type to alias",
+			commentMap: map[string]string{
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry":       "RpmDBEntry represents all captured data from a RPM DB package entry.",
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry.Name":  "Name is the RPM package name.",
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry.Epoch": "Epoch is the version epoch.",
+			},
+			aliases: map[string]string{
+				"RpmArchive": "RpmDBEntry",
+			},
+			wantComments: map[string]string{
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry":       "RpmDBEntry represents all captured data from a RPM DB package entry.",
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry.Name":  "Name is the RPM package name.",
+				"github.com/anchore/syft/syft/pkg.RpmDBEntry.Epoch": "Epoch is the version epoch.",
+				"github.com/anchore/syft/syft/pkg.RpmArchive.Name":  "Name is the RPM package name.",
+				"github.com/anchore/syft/syft/pkg.RpmArchive.Epoch": "Epoch is the version epoch.",
+			},
+		},
+		{
+			name: "handles multiple aliases",
+			commentMap: map[string]string{
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry":              "DpkgDBEntry represents data from dpkg.",
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry.Package":      "Package is the package name.",
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry.Architecture": "Architecture is the target arch.",
+			},
+			aliases: map[string]string{
+				"DpkgArchiveEntry": "DpkgDBEntry",
+				"DpkgSnapshot":     "DpkgDBEntry",
+			},
+			wantComments: map[string]string{
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry":                   "DpkgDBEntry represents data from dpkg.",
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry.Package":           "Package is the package name.",
+				"github.com/anchore/syft/syft/pkg.DpkgDBEntry.Architecture":      "Architecture is the target arch.",
+				"github.com/anchore/syft/syft/pkg.DpkgArchiveEntry.Package":      "Package is the package name.",
+				"github.com/anchore/syft/syft/pkg.DpkgArchiveEntry.Architecture": "Architecture is the target arch.",
+				"github.com/anchore/syft/syft/pkg.DpkgSnapshot.Package":          "Package is the package name.",
+				"github.com/anchore/syft/syft/pkg.DpkgSnapshot.Architecture":     "Architecture is the target arch.",
+			},
+		},
+		{
+			name: "does not copy non-field comments",
+			commentMap: map[string]string{
+				"github.com/anchore/syft/syft/pkg.SomeType":       "SomeType struct comment.",
+				"github.com/anchore/syft/syft/pkg.SomeType.Field": "Field comment.",
+			},
+			aliases: map[string]string{
+				"AliasType": "SomeType",
+			},
+			wantComments: map[string]string{
+				"github.com/anchore/syft/syft/pkg.SomeType":        "SomeType struct comment.",
+				"github.com/anchore/syft/syft/pkg.SomeType.Field":  "Field comment.",
+				"github.com/anchore/syft/syft/pkg.AliasType.Field": "Field comment.",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// create temp dir for testing
+			tmpDir := t.TempDir()
+
+			// create a test go file with type aliases
+			testFile := filepath.Join(tmpDir, "test.go")
+			content := "package test\n\n"
+			for alias, source := range tt.aliases {
+				content += "type " + alias + " " + source + "\n"
+			}
+			err := os.WriteFile(testFile, []byte(content), 0644)
+			require.NoError(t, err)
+
+			// make a copy of the comment map since the function modifies it
+			commentMap := make(map[string]string)
+			for k, v := range tt.commentMap {
+				commentMap[k] = v
+			}
+
+			// run the function
+			copyAliasFieldComments(commentMap, tmpDir)
+
+			// verify results
+			assert.Equal(t, tt.wantComments, commentMap)
+		})
+	}
+}
+
+func TestFindTypeAliases(t *testing.T) {
+	tests := []struct {
+		name        string
+		fileContent string
+		wantAliases map[string]string
+	}{
+		{
+			name: "finds simple type alias",
+			fileContent: `package test
+
+type RpmArchive RpmDBEntry
+type DpkgArchiveEntry DpkgDBEntry
+`,
+			wantAliases: map[string]string{
+				"RpmArchive":       "RpmDBEntry",
+				"DpkgArchiveEntry": "DpkgDBEntry",
+			},
+		},
+		{
+			name: "ignores struct definitions",
+			fileContent: `package test
+
+type MyStruct struct {
+	Field string
+}
+
+type AliasType BaseType
+`,
+			wantAliases: map[string]string{
+				"AliasType": "BaseType",
+			},
+		},
+		{
+			name: "ignores interface definitions",
+			fileContent: `package test
+
+type MyInterface interface {
+	Method()
+}
+
+type AliasType BaseType
+`,
+			wantAliases: map[string]string{
+				"AliasType": "BaseType",
+			},
+		},
+		{
+			name: "handles multiple files",
+			fileContent: `package test
+
+type Alias1 Base1
+type Alias2 Base2
+`,
+			wantAliases: map[string]string{
+				"Alias1": "Base1",
+				"Alias2": "Base2",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// create temp dir
+			tmpDir := t.TempDir()
+
+			// write test file
+			testFile := filepath.Join(tmpDir, "test.go")
+			err := os.WriteFile(testFile, []byte(tt.fileContent), 0644)
+			require.NoError(t, err)
+
+			// run function
+			aliases := findTypeAliases(tmpDir)
+
+			// verify
+			assert.Equal(t, tt.wantAliases, aliases)
+		})
+	}
+}
+
+func TestHasDescriptionInAlternatives(t *testing.T) {
+	tests := []struct {
+		name   string
+		schema *jsonschema.Schema
+		want   bool
+	}{
+		{
+			name: "returns true when oneOf has description",
+			schema: &jsonschema.Schema{
+				OneOf: []*jsonschema.Schema{
+					{Description: "First alternative"},
+					{Type: "null"},
+				},
+			},
+			want: true,
+		},
+		{
+			name: "returns true when anyOf has description",
+			schema: &jsonschema.Schema{
+				AnyOf: []*jsonschema.Schema{
+					{Description: "First alternative"},
+					{Type: "null"},
+				},
+			},
+			want: true,
+		},
+		{
+			name: "returns false when no alternatives have descriptions",
+			schema: &jsonschema.Schema{
+				OneOf: []*jsonschema.Schema{
+					{Type: "integer"},
+					{Type: "null"},
+				},
+			},
+			want: false,
+		},
+		{
+			name: "returns false when no oneOf or anyOf",
+			schema: &jsonschema.Schema{
+				Type: "string",
+			},
+			want: false,
+		},
+		{
+			name: "returns true when any alternative in oneOf has description",
+			schema: &jsonschema.Schema{
+				OneOf: []*jsonschema.Schema{
+					{Type: "integer"},
+					{Type: "string", Description: "Second alternative"},
+					{Type: "null"},
+				},
+			},
+			want: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := hasDescriptionInAlternatives(tt.schema)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestWarnMissingDescriptions(t *testing.T) {
+	tests := []struct {
+		name              string
+		schema            *jsonschema.Schema
+		metadataNames     []string
+		wantTypeWarnings  int
+		wantFieldWarnings int
+	}{
+		{
+			name: "no warnings when all types have descriptions",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Description: "Type A description",
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {Type: "string", Description: "Field 1"},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  0,
+			wantFieldWarnings: 0,
+		},
+		{
+			name: "warns about missing type description",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {Type: "string", Description: "Field 1"},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  1,
+			wantFieldWarnings: 0,
+		},
+		{
+			name: "warns about missing field description",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Description: "Type A description",
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {Type: "string"},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  0,
+			wantFieldWarnings: 1,
+		},
+		{
+			name: "skips fields with references",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Description: "Type A description",
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {Ref: "#/$defs/OtherType"},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  0,
+			wantFieldWarnings: 0,
+		},
+		{
+			name: "skips fields with items that are references",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Description: "Type A description",
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {
+								Type:  "array",
+								Items: &jsonschema.Schema{Ref: "#/$defs/OtherType"},
+							},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  0,
+			wantFieldWarnings: 0,
+		},
+		{
+			name: "skips fields with oneOf containing descriptions",
+			schema: &jsonschema.Schema{
+				Definitions: map[string]*jsonschema.Schema{
+					"TypeA": {
+						Description: "Type A description",
+						Properties: newOrderedMap(map[string]*jsonschema.Schema{
+							"field1": {
+								OneOf: []*jsonschema.Schema{
+									{Type: "integer", Description: "Integer value"},
+									{Type: "null"},
+								},
+							},
+						}),
+					},
+				},
+			},
+			metadataNames:     []string{"TypeA"},
+			wantTypeWarnings:  0,
+			wantFieldWarnings: 0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// capture stderr output would require more complex testing
+			// for now, just verify the function runs without panicking
+			require.NotPanics(t, func() {
+				warnMissingDescriptions(tt.schema, tt.metadataNames)
+			})
+		})
+	}
+}
+
+// helper to create an ordered map from a regular map
+func newOrderedMap(m map[string]*jsonschema.Schema) *orderedmap.OrderedMap {
+	om := orderedmap.New()
+	for k, v := range m {
+		om.Set(k, v)
+	}
+	return om
+}

internal/jsonschema/main.go

@@ -15,8 +15,8 @@ import (
 	"github.com/invopop/jsonschema"
 
 	"github.com/anchore/syft/internal"
+	"github.com/anchore/syft/internal/packagemetadata"
 	syftJsonModel "github.com/anchore/syft/syft/format/syftjson/model"
-	"github.com/anchore/syft/syft/internal/packagemetadata"
 )
 
 /*
@@ -26,6 +26,17 @@ are not captured (empty interfaces). This means that pkg.Package.Metadata is not
 can be extended to include specific package metadata struct shapes in the future.
 */
 
+var repoRoot string
+
+func init() {
+	var err error
+	repoRoot, err = packagemetadata.RepoRoot()
+	if err != nil {
+		fmt.Println("unable to determine repo root")
+		os.Exit(1)
+	}
+}
+
 func main() {
 	write(encode(build()))
 }
@@ -60,7 +71,7 @@ func assembleTypeContainer(items []any) (any, map[string]string) {
 	}
 
 	if len(typesMissingNames) > 0 {
-		fmt.Println("the following types are missing JSON names (manually curated in ./syft/internal/packagemetadata/names.go):")
+		fmt.Println("the following types are missing JSON names (manually curated in ./internal/packagemetadata/names.go):")
 		for _, t := range typesMissingNames {
 			fmt.Println("  - ", t.Name())
 		}
@@ -78,6 +89,38 @@ func build() *jsonschema.Schema {
 		Namer: func(r reflect.Type) string {
 			return strings.TrimPrefix(r.Name(), "JSON")
 		},
+		CommentMap: make(map[string]string),
+	}
+
+	// extract comments from Go source files to enrich schema descriptions
+	//
+	// note: AddGoComments parses from the module root and creates keys like "syft/pkg.TypeName",
+	// but the reflector expects fully qualified paths like "github.com/anchore/syft/syft/pkg.TypeName".
+	// We fix up the keys after extraction to match the expected format.
+	if err := reflector.AddGoComments("github.com/anchore/syft", repoRoot); err != nil {
+		fmt.Fprintf(os.Stderr, "warning: failed to extract Go comments: %v\n", err)
+	} else {
+		// fix up comment map keys to use fully qualified import paths
+		// note: AddGoComments includes the absolute repo path WITHOUT the leading slash
+		repoRootNoSlash := strings.TrimPrefix(repoRoot, "/")
+		fixedMap := make(map[string]string)
+		for k, v := range reflector.CommentMap {
+			newKey := k
+			if !strings.HasPrefix(k, "github.com/") {
+				// key doesn't have module prefix, add it
+				newKey = "github.com/anchore/syft/" + k
+			} else if strings.Contains(k, repoRootNoSlash) {
+				// key has the absolute repo path embedded, strip it
+				// format: github.com/anchore/syft/Users/wagoodman/code/syft-manual/syft/pkg.Type
+				// should be: github.com/anchore/syft/syft/pkg.Type
+				newKey = strings.Replace(k, repoRootNoSlash+"/", "", 1)
+			}
+			fixedMap[newKey] = v
+		}
+		reflector.CommentMap = fixedMap
+
+		// copy field comments for type aliases (e.g., type RpmArchive RpmDBEntry)
+		copyAliasFieldComments(reflector.CommentMap, repoRoot)
 	}
 
 	pkgMetadataContainer, pkgMetadataMapping := assembleTypeContainer(packagemetadata.AllTypes())
@@ -130,6 +173,9 @@ func build() *jsonschema.Schema {
 		"anyOf": metadataTypes,
 	})
 
+	// warn about missing descriptions
+	warnMissingDescriptions(documentSchema, metadataNames)
+
 	return documentSchema
 }
 
@@ -148,11 +194,6 @@ func encode(schema *jsonschema.Schema) []byte {
 }
 
 func write(schema []byte) {
-	repoRoot, err := packagemetadata.RepoRoot()
-	if err != nil {
-		fmt.Println("unable to determine repo root")
-		os.Exit(1)
-	}
 	schemaPath := filepath.Join(repoRoot, "schema", "json", fmt.Sprintf("schema-%s.json", internal.JSONSchemaVersion))
 	latestSchemaPath := filepath.Join(repoRoot, "schema", "json", "schema-latest.json")
 

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/discover_type_names.go

@@ -24,7 +24,7 @@ var knownNonMetadataTypeNames = strset.New(
 
 // these are names that would be removed due to common convention (e.g. used within another metadata type) but are
 // known to be metadata types themselves. Adding to this list will prevent the removal of the type from the schema.
-var knownMetadaTypeNames = strset.New(
+var knownMetadataTypeNames = strset.New(
 	"DotnetPortableExecutableEntry",
 )
 
@@ -72,7 +72,7 @@ func findMetadataDefinitionNames(paths ...string) ([]string, error) {
 	}
 
 	// any definition that is used within another struct should not be considered a top-level metadata definition
-	removeNames := strset.Difference(usedNames, knownMetadaTypeNames)
+	removeNames := strset.Difference(usedNames, knownMetadataTypeNames)
 	names.Remove(removeNames.List()...)
 
 	// remove known exceptions, that is, types exported in the pkg Package that are not used

internal/packagemetadata/generate/main.go

@@ -7,7 +7,7 @@ import (
 
 	"github.com/dave/jennifer/jen"
 
-	"github.com/anchore/syft/syft/internal/packagemetadata"
+	"github.com/anchore/syft/internal/packagemetadata"
 )
 
 // This program is invoked from syft/internal and generates packagemetadata/generated.go
@@ -31,7 +31,7 @@ func main() {
 	fmt.Printf("updating package metadata type list with %+v types\n", len(typeNames))
 
 	f := jen.NewFile("packagemetadata")
-	f.HeaderComment("DO NOT EDIT: generated by syft/internal/packagemetadata/generate/main.go")
+	f.HeaderComment("DO NOT EDIT: generated by internal/packagemetadata/generate/main.go")
 	f.ImportName(pkgImport, "pkg")
 	f.Comment("AllTypes returns a list of all pkg metadata types that syft supports (that are represented in the pkg.Package.Metadata field).")
 

internal/packagemetadata/generated.go

@@ -1,4 +1,4 @@
-// DO NOT EDIT: generated by syft/internal/packagemetadata/generate/main.go
+// DO NOT EDIT: generated by internal/packagemetadata/generate/main.go
 
 package packagemetadata
 
@@ -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{},
@@ -61,6 +64,7 @@ func AllTypes() []any {
 		pkg.RubyGemspec{},
 		pkg.RustBinaryAuditEntry{},
 		pkg.RustCargoLockEntry{},
+		pkg.SnapEntry{},
 		pkg.SwiftPackageManagerResolvedEntry{},
 		pkg.SwiplPackEntry{},
 		pkg.TerraformLockProviderEntry{},

internal/packagemetadata/names.go

@@ -95,13 +95,16 @@ 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
+	//nolint:staticcheck
 	jsonNames(pkg.PhpPeclEntry{}, "php-pecl-entry", "PhpPeclMetadata"),
 	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"),
@@ -115,12 +118,14 @@ var jsonTypes = makeJSONTypes(
 	jsonNames(pkg.OpamPackage{}, "opam-package"),
 	jsonNames(pkg.RustCargoLockEntry{}, "rust-cargo-lock-entry", "RustCargoPackageMetadata"),
 	jsonNamesWithoutLookup(pkg.RustBinaryAuditEntry{}, "rust-cargo-audit-entry", "RustCargoPackageMetadata"), // the legacy value is split into two types, where the other is preferred
+	jsonNames(pkg.SnapEntry{}, "snap-entry"),
 	jsonNames(pkg.WordpressPluginEntry{}, "wordpress-plugin-entry", "WordpressMetadata"),
 	jsonNames(pkg.HomebrewFormula{}, "homebrew-formula"),
 	jsonNames(pkg.LuaRocksPackage{}, "luarocks-package"),
 	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/relationship/index.go

@@ -79,6 +79,10 @@ func (i *Index) Remove(id artifact.ID) {
 
 func (i *Index) Replace(ogID artifact.ID, replacement artifact.Identifiable) {
 	for _, mapped := range fromMappedByID(i.fromID, ogID) {
+		// the stale relationship(i.e. if there's an elder ID in either side) should be discarded
+		if len(fromMappedByID(i.toID, mapped.relationship.To.ID())) == 0 {
+			continue
+		}
 		i.Add(artifact.Relationship{
 			From: replacement,
 			To:   mapped.relationship.To,
@@ -87,6 +91,10 @@ func (i *Index) Replace(ogID artifact.ID, replacement artifact.Identifiable) {
 	}
 
 	for _, mapped := range fromMappedByID(i.toID, ogID) {
+		// same as the above
+		if len(fromMappedByID(i.fromID, mapped.relationship.To.ID())) == 0 {
+			continue
+		}
 		i.Add(artifact.Relationship{
 			From: mapped.relationship.From,
 			To:   replacement,

internal/sourcemetadata/generate/main.go

@@ -6,7 +6,7 @@ import (
 
 	"github.com/dave/jennifer/jen"
 
-	"github.com/anchore/syft/syft/internal/sourcemetadata"
+	"github.com/anchore/syft/internal/sourcemetadata"
 )
 
 // This program is invoked from syft/internal and generates sourcemetadata/generated.go
@@ -25,7 +25,7 @@ func main() {
 	fmt.Printf("updating source metadata type list with %+v types\n", len(typeNames))
 
 	f := jen.NewFile("sourcemetadata")
-	f.HeaderComment("DO NOT EDIT: generated by syft/internal/sourcemetadata/generate/main.go")
+	f.HeaderComment("DO NOT EDIT: generated by internal/sourcemetadata/generate/main.go")
 	f.ImportName(srcImport, "source")
 	f.Comment("AllTypes returns a list of all source metadata types that syft supports (that are represented in the source.Description.Metadata field).")
 

internal/sourcemetadata/generated.go

@@ -1,4 +1,4 @@
-// DO NOT EDIT: generated by syft/internal/sourcemetadata/generate/main.go
+// DO NOT EDIT: generated by internal/sourcemetadata/generate/main.go
 
 package sourcemetadata
 

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"
@@ -32,6 +33,7 @@ import (
 	"github.com/anchore/syft/syft/pkg/cataloger/ruby"
 	"github.com/anchore/syft/syft/pkg/cataloger/rust"
 	sbomCataloger "github.com/anchore/syft/syft/pkg/cataloger/sbom"
+	"github.com/anchore/syft/syft/pkg/cataloger/snap"
 	"github.com/anchore/syft/syft/pkg/cataloger/swift"
 	"github.com/anchore/syft/syft/pkg/cataloger/swipl"
 	"github.com/anchore/syft/syft/pkg/cataloger/terraform"
@@ -51,6 +53,9 @@ const (
 	JavaScript = "javascript"
 	Node       = "node"
 	NPM        = "npm"
+
+	// Python ecosystem labels
+	Python = "python"
 )
 
 //nolint:funlen
@@ -108,7 +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"),
@@ -126,7 +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)
@@ -173,12 +178,14 @@ func DefaultPackageTaskFactories() Factories {
 		newSimplePackageTaskFactory(terraform.NewLockCataloger, pkgcataloging.DeclaredTag, pkgcataloging.DirectoryTag, "terraform"),
 		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 +4,7 @@ import (
 	"context"
 	"strings"
 
-	"github.com/anchore/archiver/v3"
+	intFile "github.com/anchore/syft/internal/file"
 	"github.com/anchore/syft/internal/log"
 	"github.com/anchore/syft/internal/sbomsync"
 	"github.com/anchore/syft/syft/cataloging"
@@ -57,9 +57,10 @@ 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 := intFile.IdentifyArchive(ctx, coords.RealPath, nil)
+			if format != nil && notArchiveErr == nil && !hasPackageReference(coords) {
 				s.Artifacts.Unknowns[coords] = append(s.Artifacts.Unknowns[coords], "archive not cataloged")
 			}
 		}

schema/cyclonedx/README.md

@@ -13,6 +13,6 @@ prior spec version (e.g. if updating to 1.7, compare the files in this directory
 equivalents). 
 
 One can also update the schemas and observe the errors in order to make the necessary updates. 
-At the time of writing, the cyclonedx.xsd needed modifications to link to the local spdx.xsd, 
-and also to changes the minOccurs for a license tag to 0. (The json schema does not require 
+At the time of writing, the cyclonedx.xsd needed modifications to link to the local spdx.xsd,
+and also to change the minOccurs for a license tag to 0. (The json schema does not require
 modification for the generated file to lint properly, but can simply be copy/pasted).   

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/file/coordinate_set.go

@@ -7,6 +7,7 @@ import (
 	"github.com/scylladb/go-set/strset"
 )
 
+// CoordinateSet provides a unique collection of Coordinates with set operations.
 type CoordinateSet struct {
 	set map[Coordinates]struct{}
 }

syft/file/coordinates.go

@@ -9,8 +9,11 @@ import (
 
 // Coordinates contains the minimal information needed to describe how to find a file within any possible source object (e.g. image and directory sources)
 type Coordinates struct {
-	RealPath     string `json:"path" cyclonedx:"path"`                 // The path where all path ancestors have no hardlinks / symlinks
-	FileSystemID string `json:"layerID,omitempty" cyclonedx:"layerID"` // An ID representing the filesystem. For container images, this is a layer digest. For directories or a root filesystem, this is blank.
+	// RealPath is the canonical absolute form of the path accessed (all symbolic links have been followed and relative path components like '.' and '..' have been removed).
+	RealPath string `json:"path" cyclonedx:"path"`
+
+	// FileSystemID is an ID representing and entire filesystem. For container images, this is a layer digest. For directories or a root filesystem, this is blank.
+	FileSystemID string `json:"layerID,omitempty" cyclonedx:"layerID"`
 }
 
 func NewCoordinates(realPath, fsID string) Coordinates {

syft/file/digest.go

@@ -1,6 +1,10 @@
 package file
 
+// Digest represents a cryptographic hash of file contents.
 type Digest struct {
+	// Algorithm specifies the hash algorithm used (e.g., "sha256", "md5").
 	Algorithm string `json:"algorithm"`
-	Value     string `json:"value"`
+
+	// Value is the hexadecimal string representation of the hash.
+	Value string `json:"value"`
 }

syft/file/executable.go

@@ -1,40 +1,60 @@
 package file
 
 type (
-	ExecutableFormat   string
+	// ExecutableFormat represents the binary executable format type.
+	ExecutableFormat string
+
+	// RelocationReadOnly indicates the RELRO security protection level applied to an ELF binary.
 	RelocationReadOnly string
 )
 
 const (
-	ELF   ExecutableFormat = "elf"
-	MachO ExecutableFormat = "macho"
-	PE    ExecutableFormat = "pe"
+	ELF   ExecutableFormat = "elf"   // Executable and Linkable Format used on Unix-like systems
+	MachO ExecutableFormat = "macho" // Mach object file format used on macOS and iOS
+	PE    ExecutableFormat = "pe"    // Portable Executable format used on Windows
 
-	RelocationReadOnlyNone    RelocationReadOnly = "none"
-	RelocationReadOnlyPartial RelocationReadOnly = "partial"
-	RelocationReadOnlyFull    RelocationReadOnly = "full"
+	RelocationReadOnlyNone    RelocationReadOnly = "none"    // no RELRO protection
+	RelocationReadOnlyPartial RelocationReadOnly = "partial" // partial RELRO protection
+	RelocationReadOnlyFull    RelocationReadOnly = "full"    // full RELRO protection
 )
 
+// Executable contains metadata about binary files and their security features.
 type Executable struct {
 	// Format denotes either ELF, Mach-O, or PE
 	Format ExecutableFormat `json:"format" yaml:"format" mapstructure:"format"`
 
-	HasExports          bool                 `json:"hasExports" yaml:"hasExports" mapstructure:"hasExports"`
-	HasEntrypoint       bool                 `json:"hasEntrypoint" yaml:"hasEntrypoint" mapstructure:"hasEntrypoint"`
-	ImportedLibraries   []string             `json:"importedLibraries" yaml:"importedLibraries" mapstructure:"importedLibraries"`
+	// HasExports indicates whether the binary exports symbols.
+	HasExports bool `json:"hasExports" yaml:"hasExports" mapstructure:"hasExports"`
+
+	// HasEntrypoint indicates whether the binary has an entry point function.
+	HasEntrypoint bool `json:"hasEntrypoint" yaml:"hasEntrypoint" mapstructure:"hasEntrypoint"`
+
+	// ImportedLibraries lists the shared libraries required by this executable.
+	ImportedLibraries []string `json:"importedLibraries" yaml:"importedLibraries" mapstructure:"importedLibraries"`
+
+	// ELFSecurityFeatures contains ELF-specific security hardening information when Format is ELF.
 	ELFSecurityFeatures *ELFSecurityFeatures `json:"elfSecurityFeatures,omitempty" yaml:"elfSecurityFeatures" mapstructure:"elfSecurityFeatures"`
 }
 
+// ELFSecurityFeatures captures security hardening and protection mechanisms in ELF binaries.
 type ELFSecurityFeatures struct {
+	// SymbolTableStripped indicates whether debugging symbols have been removed.
 	SymbolTableStripped bool `json:"symbolTableStripped" yaml:"symbolTableStripped" mapstructure:"symbolTableStripped"`
 
-	// classic protections
+	// StackCanary indicates whether stack smashing protection is enabled.
+	StackCanary *bool `json:"stackCanary,omitempty" yaml:"stackCanary" mapstructure:"stackCanary"`
 
-	StackCanary                   *bool              `json:"stackCanary,omitempty" yaml:"stackCanary" mapstructure:"stackCanary"`
-	NoExecutable                  bool               `json:"nx" yaml:"nx" mapstructure:"nx"`
-	RelocationReadOnly            RelocationReadOnly `json:"relRO" yaml:"relRO" mapstructure:"relRO"`
-	PositionIndependentExecutable bool               `json:"pie" yaml:"pie" mapstructure:"pie"`
-	DynamicSharedObject           bool               `json:"dso" yaml:"dso" mapstructure:"dso"`
+	// NoExecutable indicates whether NX (no-execute) protection is enabled for the stack.
+	NoExecutable bool `json:"nx" yaml:"nx" mapstructure:"nx"`
+
+	// RelocationReadOnly indicates the RELRO protection level.
+	RelocationReadOnly RelocationReadOnly `json:"relRO" yaml:"relRO" mapstructure:"relRO"`
+
+	// PositionIndependentExecutable indicates whether the binary is compiled as PIE.
+	PositionIndependentExecutable bool `json:"pie" yaml:"pie" mapstructure:"pie"`
+
+	// DynamicSharedObject indicates whether the binary is a shared library.
+	DynamicSharedObject bool `json:"dso" yaml:"dso" mapstructure:"dso"`
 
 	// LlvmSafeStack represents a compiler-based security mechanism that separates the stack into a safe stack for storing return addresses and other critical data, and an unsafe stack for everything else, to mitigate stack-based memory corruption errors
 	// see https://clang.llvm.org/docs/SafeStack.html

syft/file/license.go

@@ -5,18 +5,33 @@ import (
 	"github.com/anchore/syft/syft/license"
 )
 
+// License represents license information discovered within a file.
 type License struct {
-	Value           string
-	SPDXExpression  string
-	Type            license.Type
-	LicenseEvidence *LicenseEvidence // evidence from license classifier
-	Contents        string           `hash:"ignore"`
+	// Value is the raw license string as found in the file.
+	Value string
+
+	// SPDXExpression is the parsed SPDX license expression if available.
+	SPDXExpression string
+
+	// Type categorizes how the license was determined (e.g., declared, concluded -- following the same semantics as SPDX).
+	Type license.Type
+
+	LicenseEvidence *LicenseEvidence
+
+	// Contents optionally stores the full license text.
+	Contents string `hash:"ignore"`
 }
 
+// LicenseEvidence contains details from license classifier analysis.
 type LicenseEvidence struct {
+	// Confidence is a score indicating certainty of the license match.
 	Confidence int
-	Offset     int
-	Extent     int
+
+	// Offset is the byte position where the license text begins in the file.
+	Offset int
+
+	// Extent is the length in bytes of the matched license text.
+	Extent int
 }
 
 func NewLicense(value string) License {

syft/file/location.go

@@ -27,18 +27,24 @@ type Location struct {
 	LocationMetadata `cyclonedx:""`
 }
 
+// LocationData contains the core identifying information for a file location.
 type LocationData struct {
 	Coordinates `cyclonedx:""` // Empty string here means there is no intermediate property name, e.g. syft:locations:0:path without "coordinates"
 	// note: it is IMPORTANT to ignore anything but the coordinates for a Location when considering the ID (hash value)
 	// since the coordinates are the minimally correct ID for a location (symlinks should not come into play)
-	AccessPath string         `hash:"ignore" json:"accessPath"` // The path to the file which may or may not have hardlinks / symlinks
-	ref        file.Reference `hash:"ignore"`                   // The file reference relative to the stereoscope.FileCatalog that has more information about this location.
+
+	// AccessPath is the path used to retrieve file contents (which may or may not have hardlinks / symlinks in the path)
+	AccessPath string `hash:"ignore" json:"accessPath"`
+
+	// ref is the stereoscope file reference relative to the stereoscope.FileCatalog that has more information about this location.
+	ref file.Reference `hash:"ignore"`
 }
 
 func (l LocationData) Reference() file.Reference {
 	return l.ref
 }
 
+// LocationMetadata provides additional contextual information about a file location.
 type LocationMetadata struct {
 	Annotations map[string]string `json:"annotations,omitempty"` // Arbitrary key-value pairs that can be used to annotate a location
 }

syft/file/location_read_closer.go

@@ -2,6 +2,7 @@ package file
 
 import "io"
 
+// LocationReadCloser combines a Location with a ReadCloser for accessing file content with location metadata.
 type LocationReadCloser struct {
 	Location
 	io.ReadCloser

syft/file/location_set.go

@@ -9,6 +9,7 @@ import (
 	"github.com/anchore/syft/internal/log"
 )
 
+// LocationSet provides a unique collection of Locations with metadata and set operations.
 type LocationSet struct {
 	set map[LocationData]LocationMetadata
 }

syft/file/locations.go

@@ -8,6 +8,7 @@ import (
 
 var locationSorterWithoutLayers = LocationSorter(nil)
 
+// Locations is a sortable slice of Location values.
 type Locations []Location
 
 func (l Locations) Len() int {

syft/file/resolver.go

@@ -18,6 +18,7 @@ type ContentResolver interface {
 	FileContentsByLocation(Location) (io.ReadCloser, error)
 }
 
+// MetadataResolver provides file metadata lookup by location.
 type MetadataResolver interface {
 	FileMetadataByLocation(Location) (Metadata, error)
 }
@@ -51,6 +52,7 @@ type PathResolver interface {
 	RelativeFileByPath(_ Location, path string) *Location
 }
 
+// LocationResolver provides iteration over all file locations in a source.
 type LocationResolver interface {
 	// AllLocations returns a channel of all file references from the underlying source.
 	// The implementation for this may vary, however, generally the following considerations should be made:
@@ -59,6 +61,7 @@ type LocationResolver interface {
 	AllLocations(ctx context.Context) <-chan Location
 }
 
+// WritableResolver extends Resolver with the ability to write file content.
 type WritableResolver interface {
 	Resolver
 

syft/file/search_result.go

@@ -4,13 +4,25 @@ import (
 	"fmt"
 )
 
+// SearchResult represents a match found during content scanning, such as secret detection.
 type SearchResult struct {
+	// Classification identifies the type or category of the matched content.
 	Classification string `json:"classification"`
-	LineNumber     int64  `json:"lineNumber"`
-	LineOffset     int64  `json:"lineOffset"`
-	SeekPosition   int64  `json:"seekPosition"`
-	Length         int64  `json:"length"`
-	Value          string `json:"value,omitempty"`
+
+	// LineNumber is the 1-indexed line number where the match was found.
+	LineNumber int64 `json:"lineNumber"`
+
+	// LineOffset is the character offset from the start of the line where the match begins.
+	LineOffset int64 `json:"lineOffset"`
+
+	// SeekPosition is the absolute byte offset from the start of the file.
+	SeekPosition int64 `json:"seekPosition"`
+
+	// Length is the size in bytes of the matched content.
+	Length int64 `json:"length"`
+
+	// Value optionally contains the actual matched content.
+	Value string `json:"value,omitempty"`
 }
 
 func (s SearchResult) String() string {

syft/file/selection.go

@@ -1,9 +1,10 @@
 package file
 
 const (
-	NoFilesSelection             Selection = "none"
-	FilesOwnedByPackageSelection Selection = "owned-by-package"
-	AllFilesSelection            Selection = "all"
+	NoFilesSelection             Selection = "none"             // no files are selected
+	FilesOwnedByPackageSelection Selection = "owned-by-package" // only files owned by packages are selected
+	AllFilesSelection            Selection = "all"              // all files are selected
 )
 
+// Selection defines which files should be included during cataloging operations.
 type Selection string

syft/format/common/spdxhelpers/to_format_model_test.go

@@ -15,10 +15,10 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"github.com/anchore/syft/internal/relationship"
+	"github.com/anchore/syft/internal/sourcemetadata"
 	"github.com/anchore/syft/syft/artifact"
 	"github.com/anchore/syft/syft/file"
 	"github.com/anchore/syft/syft/format/internal/spdxutil/helpers"
-	"github.com/anchore/syft/syft/internal/sourcemetadata"
 	"github.com/anchore/syft/syft/pkg"
 	"github.com/anchore/syft/syft/sbom"
 	"github.com/anchore/syft/syft/source"