Author SHA1 Message Date
sneak cc6dc9199f Validate manifest entry paths on deserialize (closes #61)
check / check (push) Successful in 1m48s
Untrusted .mf files were parsed with no path validation, so an entry
like ../../etc/passwd flowed into filepath.Join against the checker's
base path. ValidatePath ran only on the write side (Builder). Enforce it
on every entry in deserializeInner, so all consumers — Checker now, any
restore/extract path later — are protected. Reject the whole manifest on
the first offender rather than dropping entries, which could hide files
from a check; failures wrap a new errInvalidManifestPath sentinel and
name the path.

A path that is not valid UTF-8 is refused at load time by the proto3
string decoder before validation runs; the test covers that plus the
traversal, absolute, backslash, and empty cases, and a valid round-trip.

Model: opus-4-8
2026-09-21 07:45:02 +00:00
11 changed files with 224 additions and 90 deletions
-12
View File
@@ -1,12 +0,0 @@
root = true
[*]
indent_style = space
indent_size = 4
end_of_line = lf
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
[Makefile]
indent_style = tab
+2 -21
View File
@@ -10,24 +10,5 @@ modcache.tzst
# Generated manifest files # Generated manifest files
.index.mf .index.mf
# Secrets # Stale files
.env .drone.yml
.env.*
*.key
*.pem
# OS files
.DS_Store
Thumbs.db
# Editor files
*.swp
*.swo
*~
.idea/
.vscode/
# Go build artifacts
*.log
*.out
*.test
+3 -6
View File
@@ -24,12 +24,8 @@ only thing left of the `chore/align-repo-policies` branch is the list below.
# Completed Steps # Completed Steps
- 2026-09-21: rewrote `script/test` to the canonical pattern (30s timeout, - 2026-09-21: validate manifest entry paths on deserialize so untrusted `.mf`
`-race -cover`, quiet-first with verbose-on-failure rerun) and fixed the files cannot make `Checker` stat or read outside `basePath` (#61)
process-global logger data race it surfaced (#67)
- 2026-09-21: added the canonical `.editorconfig`, made `.gitignore` cover
secrets, OS, editor, and Go artifacts, and removed the dead Drone CI
references from `.gitignore` and `bin/gitrev.sh` (#72)
- 2026-08-09: added `.prettierrc`/`.prettierignore`, gave `script/fmt` and - 2026-08-09: added `.prettierrc`/`.prettierignore`, gave `script/fmt` and
`script/fmt-check` one shared prettier file set via `script/prettier`, dropped `script/fmt-check` one shared prettier file set via `script/prettier`, dropped
the `|| true` that hid prettier failures, and added a node-based Dockerfile the `|| true` that hid prettier failures, and added a node-based Dockerfile
@@ -68,6 +64,7 @@ only thing left of the `chore/align-repo-policies` branch is the list below.
- Move FORMAT.md from repo root to docs/ and update the AGENTS.md reference - Move FORMAT.md from repo root to docs/ and update the AGENTS.md reference
- Pin Makefile-installed Go tools (`protoc-gen-go@v1.28.1`, - Pin Makefile-installed Go tools (`protoc-gen-go@v1.28.1`,
`golangci-lint@v2.12.2`) by module hash, not mutable tag `golangci-lint@v2.12.2`) by module hash, not mutable tag
- Set `make test` timeout to 30s (currently 10s)
- Add explicit README "Rationale" heading (content exists under other - Add explicit README "Rationale" heading (content exists under other
names); name the author in the README Description first line names); name the author in the README Description first line
- Reconcile root-level AGENTS.md with directory-hygiene policy (keep or - Reconcile root-level AGENTS.md with directory-hygiene policy (keep or
+5
View File
@@ -1,5 +1,10 @@
#!/bin/bash #!/bin/bash
# #
if [[ ! -z "$DRONE_COMMIT_SHA" ]]; then
echo "${DRONE_COMMIT_SHA:0:7}"
exit 0
fi
if [[ ! -z "$GITREV" ]]; then if [[ ! -z "$GITREV" ]]; then
echo $GITREV echo $GITREV
else else
+8 -10
View File
@@ -679,13 +679,11 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
fs := afero.NewMemMapFs() fs := afero.NewMemMapFs()
rng := rand.New(rand.NewSource(42)) //nolint:gosec // deterministic test data rng := rand.New(rand.NewSource(42)) //nolint:gosec // deterministic test data
// Create many small files with random names so the manifest has many // Create many small files with random names to generate a ~1MB manifest
// entries and random single-byte flips land at varied offsets. Each // Each manifest entry is roughly 50-60 bytes, so we need ~20000 files
// manifest entry is roughly 50-60 bytes. Kept modest so the suite stays
// within its wall-clock budget under -race.
require.NoError(t, fs.MkdirAll(testDir, 0o755)) require.NoError(t, fs.MkdirAll(testDir, 0o755))
numFiles := 1500 numFiles := 20000
for range numFiles { for range numFiles {
// Generate random filename // Generate random filename
filename := fmt.Sprintf("/testdir/%08x%08x%08x.dat", filename := fmt.Sprintf("/testdir/%08x%08x%08x.dat",
@@ -701,11 +699,11 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
exitCode := runCLI(opts) exitCode := runCLI(opts)
require.Equal(t, 0, exitCode, "generate should succeed") require.Equal(t, 0, exitCode, "generate should succeed")
// Read the valid manifest and verify it has real size. // Read the valid manifest and verify it's approximately 1MB
validManifest, err := afero.ReadFile(fs, testManifest) validManifest, err := afero.ReadFile(fs, testManifest)
require.NoError(t, err) require.NoError(t, err)
require.GreaterOrEqual(t, len(validManifest), 64*1024, require.GreaterOrEqual(t, len(validManifest), 1024*1024,
"manifest should be at least 64KB, got %d bytes", len(validManifest)) "manifest should be at least 1MB, got %d bytes", len(validManifest))
t.Logf("manifest size: %d bytes (%d files)", len(validManifest), numFiles) t.Logf("manifest size: %d bytes (%d files)", len(validManifest), numFiles)
// First corruption: truncate the manifest // First corruption: truncate the manifest
@@ -728,8 +726,8 @@ func TestCheckDetectsManifestCorruption(t *testing.T) {
exitCode = runCLI(opts) exitCode = runCLI(opts)
require.Equal(t, 0, exitCode, "check should pass with valid manifest") require.Equal(t, 0, exitCode, "check should pass with valid manifest")
// Now do 100 random corruption iterations // Now do 500 random corruption iterations
for i := range 100 { for i := range 500 {
// Corrupt: write a random byte at a random offset // Corrupt: write a random byte at a random offset
corrupted := make([]byte, len(validManifest)) corrupted := make([]byte, len(validManifest))
copy(corrupted, validManifest) copy(corrupted, validManifest)
+1 -1
View File
@@ -357,6 +357,6 @@ func (mfa *CLIApp) run(args []string) {
if err != nil { if err != nil {
mfa.exitCode = 1 mfa.exitCode = 1
log.Errorf("%s", err) log.WithError(err).Debugf("exiting")
} }
} }
+41 -34
View File
@@ -112,16 +112,13 @@ func DisableStyling() {
} }
// Init initializes the logger with the CLI handler and default log level. // Init initializes the logger with the CLI handler and default log level.
//
// It reconfigures the process-global apex/log logger under the write lock so
// the global is never mutated while another goroutine holds the read lock to
// read it in emit. Without this, parallel callers (e.g. the test suite) race
// Init's SetLevel/SetHandler against concurrent log calls.
func Init() { func Init() {
mu.Lock() mu.RLock()
defer mu.Unlock()
log.SetHandler(acli.New(stderr)) w := stderr
mu.RUnlock()
log.SetHandler(acli.New(w))
log.SetLevel(log.DebugLevel) // Let apex/log pass everything; we filter ourselves log.SetLevel(log.DebugLevel) // Let apex/log pass everything; we filter ourselves
} }
@@ -133,66 +130,74 @@ func isEnabled(l Level) bool {
return l >= currentLevel return l >= currentLevel
} }
// emit calls fn while holding the read lock if messages at level l are
// enabled. Holding the read lock across the apex/log call keeps the global
// logger from being read while Init reconfigures it under the write lock.
func emit(l Level, fn func()) {
mu.RLock()
defer mu.RUnlock()
if l >= currentLevel {
fn()
}
}
// Fatalf logs a formatted message at fatal level. // Fatalf logs a formatted message at fatal level.
func Fatalf(format string, args ...any) { func Fatalf(format string, args ...any) {
emit(FatalLevel, func() { log.Fatalf(format, args...) }) if isEnabled(FatalLevel) {
log.Fatalf(format, args...)
}
} }
// Fatal logs a message at fatal level. // Fatal logs a message at fatal level.
func Fatal(arg string) { func Fatal(arg string) {
emit(FatalLevel, func() { log.Fatal(arg) }) if isEnabled(FatalLevel) {
log.Fatal(arg)
}
} }
// Errorf logs a formatted message at error level. // Errorf logs a formatted message at error level.
func Errorf(format string, args ...any) { func Errorf(format string, args ...any) {
emit(ErrorLevel, func() { log.Errorf(format, args...) }) if isEnabled(ErrorLevel) {
log.Errorf(format, args...)
}
} }
// Error logs a message at error level. // Error logs a message at error level.
func Error(arg string) { func Error(arg string) {
emit(ErrorLevel, func() { log.Error(arg) }) if isEnabled(ErrorLevel) {
log.Error(arg)
}
} }
// Warnf logs a formatted message at warn level. // Warnf logs a formatted message at warn level.
func Warnf(format string, args ...any) { func Warnf(format string, args ...any) {
emit(WarnLevel, func() { log.Warnf(format, args...) }) if isEnabled(WarnLevel) {
log.Warnf(format, args...)
}
} }
// Warn logs a message at warn level. // Warn logs a message at warn level.
func Warn(arg string) { func Warn(arg string) {
emit(WarnLevel, func() { log.Warn(arg) }) if isEnabled(WarnLevel) {
log.Warn(arg)
}
} }
// Infof logs a formatted message at info level. // Infof logs a formatted message at info level.
func Infof(format string, args ...any) { func Infof(format string, args ...any) {
emit(InfoLevel, func() { log.Infof(format, args...) }) if isEnabled(InfoLevel) {
log.Infof(format, args...)
}
} }
// Info logs a message at info level. // Info logs a message at info level.
func Info(arg string) { func Info(arg string) {
emit(InfoLevel, func() { log.Info(arg) }) if isEnabled(InfoLevel) {
log.Info(arg)
}
} }
// Verbosef logs a formatted message at verbose level. // Verbosef logs a formatted message at verbose level.
func Verbosef(format string, args ...any) { func Verbosef(format string, args ...any) {
emit(VerboseLevel, func() { log.Infof(format, args...) }) if isEnabled(VerboseLevel) {
log.Infof(format, args...)
}
} }
// Verbose logs a message at verbose level. // Verbose logs a message at verbose level.
func Verbose(arg string) { func Verbose(arg string) {
emit(VerboseLevel, func() { log.Info(arg) }) if isEnabled(VerboseLevel) {
log.Info(arg)
}
} }
// Debugf logs a formatted message at debug level with caller location. // Debugf logs a formatted message at debug level with caller location.
@@ -211,10 +216,7 @@ func Debug(arg string) {
// DebugReal logs at debug level with caller info from the specified stack depth. // DebugReal logs at debug level with caller info from the specified stack depth.
func DebugReal(arg string, cs int) { func DebugReal(arg string, cs int) {
mu.RLock() if !isEnabled(DebugLevel) {
defer mu.RUnlock()
if DebugLevel < currentLevel {
return return
} }
@@ -273,6 +275,11 @@ func GetLevel() Level {
return currentLevel return currentLevel
} }
// WithError returns a log entry with the error attached.
func WithError(e error) *log.Entry {
return log.Log.WithError(e)
}
// Progressf prints a progress message that overwrites the current line. // Progressf prints a progress message that overwrites the current line.
// Use ProgressDone() when progress is complete to move to the next line. // Use ProgressDone() when progress is complete to move to the next line.
func Progressf(format string, args ...any) { func Progressf(format string, args ...any) {
+4
View File
@@ -312,6 +312,10 @@ func (c *Checker) FindExtraFiles(ctx context.Context, results chan<- Result) err
} }
func (c *Checker) checkFile(entry *MFFilePath, checkedBytes *FileSize) Result { func (c *Checker) checkFile(entry *MFFilePath, checkedBytes *FileSize) Result {
// entry.GetPath() is safe to join here: a manifest's entry paths are
// validated against the path invariants when it is loaded (see
// deserializeInner) or built (see Builder.AddFile), so a traversal or
// absolute path can never reach this point.
absPath := filepath.Join(string(c.basePath), entry.GetPath()) absPath := filepath.Join(string(c.basePath), entry.GetPath())
relPath := RelFilePath(entry.GetPath()) relPath := RelFilePath(entry.GetPath())
+14
View File
@@ -25,6 +25,7 @@ var (
errDecompressedTooLarge = errors.New("decompressed data exceeds maximum allowed size") errDecompressedTooLarge = errors.New("decompressed data exceeds maximum allowed size")
errUUIDMismatch = errors.New("outer and inner UUID mismatch") errUUIDMismatch = errors.New("outer and inner UUID mismatch")
errInvalidFileFormat = errors.New("invalid file format") errInvalidFileFormat = errors.New("invalid file format")
errInvalidManifestPath = errors.New("manifest contains invalid path")
) )
// validateUUID checks that the byte slice is a valid UUID (16 bytes, parseable). // validateUUID checks that the byte slice is a valid UUID (16 bytes, parseable).
@@ -181,6 +182,19 @@ func (m *manifest) deserializeInner() error {
return errUUIDMismatch return errUUIDMismatch
} }
// Enforce the manifest path invariants on every entry as it is loaded,
// so that no consumer of a manifest — Checker today, any restore or
// extract path tomorrow — acts on a traversal or absolute path from an
// untrusted .mf. Reject loudly on the first offender rather than
// dropping entries, which would let a hostile manifest hide files from a
// check.
for _, f := range m.pbInner.GetFiles() {
err = ValidatePath(f.GetPath())
if err != nil {
return fmt.Errorf("%w: %w", errInvalidManifestPath, err)
}
}
log.Infof("loaded manifest with %d files", len(m.pbInner.GetFiles())) log.Infof("loaded manifest with %d files", len(m.pbInner.GetFiles()))
return nil return nil
+145
View File
@@ -0,0 +1,145 @@
//nolint:testpackage // white-box tests exercise unexported internals
package mfer
import (
"bytes"
"crypto/sha256"
"fmt"
"testing"
"github.com/google/uuid"
"github.com/klauspost/compress/zstd"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"google.golang.org/protobuf/encoding/protowire"
"google.golang.org/protobuf/proto"
)
// craftInnerBytes builds the wire bytes of an inner MFFile holding a single
// file entry whose path is exactly pathBytes. It writes the wire form by hand
// so a hostile path — including one that is not valid UTF-8 — can be embedded
// without proto.Marshal's own UTF-8 enforcement rejecting it first.
func craftInnerBytes(id uuid.UUID, pathBytes string) []byte {
entry := protowire.AppendTag(nil, 1, protowire.BytesType) // MFFilePath.path
entry = protowire.AppendString(entry, pathBytes)
inner := protowire.AppendTag(nil, 100, protowire.VarintType) // MFFile.version
inner = protowire.AppendVarint(inner, uint64(MFFile_VERSION_ONE))
inner = protowire.AppendTag(inner, 101, protowire.BytesType) // MFFile.files
inner = protowire.AppendBytes(inner, entry)
inner = protowire.AppendTag(inner, 102, protowire.BytesType) // MFFile.uuid
inner = protowire.AppendBytes(inner, id[:])
return inner
}
// wrapInner wraps inner MFFile wire bytes in a complete, well-formed .mf
// envelope (magic prefix, zstd-compressed payload, matching hash and UUID) so
// that deserialization reaches path validation rather than failing earlier on
// an integrity check.
func wrapInner(t *testing.T, id uuid.UUID, innerData []byte) []byte {
t.Helper()
var cbuf bytes.Buffer
zw, err := zstd.NewWriter(&cbuf, zstd.WithEncoderLevel(zstd.SpeedBestCompression))
require.NoError(t, err)
_, err = zw.Write(innerData)
require.NoError(t, err)
require.NoError(t, zw.Close())
compressed := cbuf.Bytes()
sum := sha256.Sum256(compressed)
outer := &MFFileOuter{
InnerMessage: compressed,
Size: int64(len(innerData)),
Sha256: sum[:],
Uuid: id[:],
Version: MFFileOuter_VERSION_ONE,
CompressionType: MFFileOuter_COMPRESSION_ZSTD,
}
ob, err := proto.Marshal(outer)
require.NoError(t, err)
return append([]byte(MAGIC), ob...)
}
func TestDeserializeRejectsInvalidEntryPaths(t *testing.T) {
t.Parallel()
tests := []struct {
name string
path string
}{
{"parent traversal", "../escape"},
{"interior traversal", "a/../../escape"},
{"absolute path", "/etc/passwd"},
{"backslash path", `a\b`},
{"double slash", "a//b"},
{"empty path", ""},
{"invalid utf-8", "abc\xff"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
id := uuid.New()
data := wrapInner(t, id, craftInnerBytes(id, tt.path))
_, err := NewManifestFromReader(bytes.NewReader(data))
require.Error(t, err)
if tt.path == "abc\xff" {
// A path that is not valid UTF-8 cannot survive the proto3
// string decoder, which rejects it before path validation
// runs; the manifest is still refused at load time.
return
}
require.ErrorIs(t, err, errInvalidManifestPath)
if tt.path != "" {
// ValidatePath quotes the path with %q; assert against the
// same rendering so escaped characters (e.g. a backslash)
// still match.
assert.Contains(t, err.Error(), fmt.Sprintf("%q", tt.path),
"error must name the offending path")
}
})
}
}
func TestDeserializeValidManifestRoundTrips(t *testing.T) {
t.Parallel()
hash := make([]byte, 34) // multihash: 2-byte prefix + 32-byte SHA-256
b := NewBuilder()
require.NoError(t, b.AddFileWithHash("dir/file.txt", 123, ModTime{}, hash))
var buf bytes.Buffer
require.NoError(t, b.Build(&buf))
m, err := NewManifestFromReader(bytes.NewReader(buf.Bytes()))
require.NoError(t, err)
files := m.Files()
require.Len(t, files, 1)
assert.Equal(t, "dir/file.txt", files[0].GetPath())
assert.Equal(t, int64(123), files[0].GetSize())
}
// TestValidatePathRejectsInvalidUTF8 pins the ValidatePath rule that a manifest
// path must be valid UTF-8, independent of the proto decoder that also enforces
// it on the wire.
func TestValidatePathRejectsInvalidUTF8(t *testing.T) {
t.Parallel()
err := ValidatePath("abc\xff")
require.ErrorIs(t, err, errPathNotUTF8)
assert.Contains(t, err.Error(), "UTF-8")
}
+1 -6
View File
@@ -17,12 +17,7 @@ ensure_pb() {
main() { main() {
cd "$ROOT" cd "$ROOT"
ensure_pb ensure_pb
go test -timeout 30s -race -cover ./... || go test -v --timeout 10s ./...
{
echo "--- Rerunning with -v for details ---"
go test -timeout 30s -race -v ./...
exit 1
}
} }
main "$@" main "$@"