fix: bound total decompression under each top-level archive

the limiter bounds what's held *at once*, and each archive gives its bytes back when it's released. So a recursive bomb (42.zip shape) never trips a limit: every level fits on its own, and the scan just runs for effectively forever. Capping each archive at N× its own size wouldn't help either, since every level of such a bomb is high-ratio, so the work still grows about N-fold per level.

- each top-level archive gets one decompression budget of `max(100 × its size, 1 GiB)`, spent by every archive nested under it at any depth
- the budget is attached to the context when the walk enters a top-level archive, so `Extract` picks it up without a signature change
- once it's spent, the archive being extracted is truncated with a "possible decompression bomb" unknown and the walk moves on. The next top-level archive starts fresh

real trees (a war of jars, a layer of tarballs) expand a few times over, well under the ratio.

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

internal/archive/extract.go

@@ -152,6 +152,10 @@ func (r *Resolver) extract(ctx context.Context, format archives.Extractor, conte
 		r.truncate("extraction stopped at the configured memory or disk limit")
 		return nil
 	}
+	if errors.Is(err, errBudgetSpent) {
+		r.truncate("extraction stopped: the archive and those nested in it decompressed to far more than its size (possible decompression bomb)")
+		return nil
+	}
 	return err
 }
 

internal/archive/limits.go

@@ -5,6 +5,35 @@ import (
 	"sync"
 )
 
+// Budget bounds the bytes decompressed under one top-level archive, summed over every archive nested in
+// it. Unlike Limits it never refills as archives are released: it bounds work, not what is held at once,
+// which is what stops a recursive bomb (42.zip) whose every level fits the limits on its own. A nil
+// *Budget admits everything.
+//
+// ponytail: no lock, since the archive walk is sequential; guard it if the walk ever runs concurrently.
+type Budget struct {
+	remaining int64
+}
+
+func NewBudget(bytes int64) *Budget {
+	return &Budget{remaining: bytes}
+}
+
+// take spends n bytes, or reports false (and spends the rest) when fewer than n remain.
+func (b *Budget) take(n int64) bool {
+	if b == nil {
+		return true
+	}
+	if n > b.remaining {
+		b.remaining = 0
+		return false
+	}
+	b.remaining -= n
+	return true
+}
+
+var errBudgetSpent = errors.New("archive tree decompression budget spent")
+
 // ErrDiskLimitReached reports that placing an archive's content would exceed the disk limit.
 var ErrDiskLimitReached = errors.New("archive content would exceed the disk limit")
 

internal/archive/resolver.go

@@ -35,13 +35,14 @@ type Resolver struct {
 	Digests []file.Digest
 
 	// Truncated reports that the resolver covers only part of the archive, and TruncatedReason says why:
-	// the disk limit stopped extraction early, or an entry was too large to store.
+	// the disk limit or the decompression budget stopped extraction early, or an entry was too large.
 	Truncated       bool
 	TruncatedReason string
 
 	fileSystemID string
 	archivePath  string
 	charge       *charge
+	budget       *Budget
 
 	// content is held in memory while the memory limit admits it and in one spill file once it does
 	// not. The file is created on first use, so an archive that stays in memory never touches the
@@ -92,6 +93,7 @@ func newResolver(ctx context.Context, fileSystemID, archivePath string, charge *
 		fileSystemID: fileSystemID,
 		archivePath:  archivePath,
 		charge:       charge,
+		budget:       budgetFromContext(ctx),
 		tempDir:      tmpdir.FromContext(ctx),
 		byPath:       map[string]*node{"/": {path: "/", isDir: true}},
 	}

internal/archive/storage.go

@@ -43,6 +43,9 @@ func (r *Resolver) put(b *blob, content io.Reader) error {
 	for {
 		n, readErr := content.Read(r.chunk)
 		if n > 0 {
+			if !r.budget.take(int64(n)) {
+				return errBudgetSpent
+			}
 			if err := r.write(b, r.chunk[:n]); err != nil {
 				return err
 			}

internal/archive/traversal.go

@@ -52,6 +52,19 @@ func TraversalFromContext(ctx context.Context) *Traversal {
 	return t
 }
 
+type budgetCtxKey struct{}
+
+// WithBudget sets the decompression budget that Extract spends from, for this archive and every archive
+// extracted beneath it.
+func WithBudget(ctx context.Context, b *Budget) context.Context {
+	return context.WithValue(ctx, budgetCtxKey{}, b)
+}
+
+func budgetFromContext(ctx context.Context) *Budget {
+	b, _ := ctx.Value(budgetCtxKey{}).(*Budget)
+	return b
+}
+
 type nestedCatalogingCtxKey struct{}
 
 // WithNestedCataloging marks the context of a scan whose archive cataloger task will extract every