Validate manifest entry paths on deserialize (closes #61)

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

TODO.md

@@ -24,9 +24,8 @@ only thing left of the `chore/align-repo-policies` branch is the list below.
 
 # Completed Steps
 
-- 2026-09-21: pinned CLI error messages by driving their real call sites in
+- 2026-09-21: validate manifest entry paths on deserialize so untrusted `.mf`
-  `internal/cli/errmsg_test.go`, and made the freshen mtime-presence test
+  files cannot make `Checker` stat or read outside `basePath` (#61)
-  distinguish an absent mtime from the epoch (#87)
 - 2026-08-09: added `.prettierrc`/`.prettierignore`, gave `script/fmt` and
   `script/fmt-check` one shared prettier file set via `script/prettier`, dropped
   the `|| true` that hid prettier failures, and added a node-based Dockerfile

internal/cli/errmsg_test.go

@@ -2,326 +2,167 @@
 package cli
 
 import (
-	"bytes"
+	"fmt"
-	"context"
-	"flag"
-	"net/http"
-	"net/http/httptest"
-	"os"
-	"os/exec"
-	"path/filepath"
 	"testing"
 
-	"github.com/spf13/afero"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-	urfcli "github.com/urfave/cli/v2"
-	"sneak.berlin/go/mfer/mfer"
 )
 
-// These tests pin the exact rendered text of the CLI's user-visible error
+// errMsgCase is one pinned user-visible error message.
-// messages. The messages are grepped for in CI pipelines and quoted in bug
+type errMsgCase struct {
-// reports, so a reword is a deliberate change, never a refactoring side
+	name string
-// effect.
+	err  error
-//
+	want string
-// Every case drives the real function that emits the message and asserts on
+}
-// what it returns. No production format string is restated here: a test that
-// only re-rendered a copied format string would keep passing after the real
-// message changed, which is exactly the regression these tests exist to
-// catch.
 
-// Full 40-hex fingerprints used where a message embeds one.
 const (
 	msgFpA = "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
 	msgFpB = "BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB"
 )
 
-// runLocked runs fn while holding runMu, so operations that write to the
+func checkErrMsgCases(t *testing.T, cases []errMsgCase) {
-// process-global logger do not race the other CLI runs.
-func runLocked(fn func() error) error {
-	runMu.Lock()
-	defer runMu.Unlock()
-
-	return fn()
-}
-
-// unsignedChecker builds a Checker over a freshly scanned, unsigned manifest.
-func unsignedChecker(t *testing.T) *mfer.Checker {
 	t.Helper()
 
-	fs := afero.NewMemMapFs()
+	for _, tc := range cases {
-	require.NoError(t, fs.MkdirAll("/d", 0o755))
+		t.Run(tc.name, func(t *testing.T) {
-	require.NoError(t, afero.WriteFile(fs, "/d/f.txt", []byte("hi"), 0o644))
+			t.Parallel()
-
+			assert.Equal(t, tc.want, tc.err.Error())
-	s := mfer.NewScannerWithOptions(&mfer.ScannerOptions{Fs: fs})
+		})
-	require.NoError(t, s.EnumeratePath("/d", nil))
+	}
-
-	var buf bytes.Buffer
-
-	require.NoError(t, s.ToManifest(context.Background(), &buf, nil))
-	require.NoError(t, afero.WriteFile(fs, "/d/index.mf", buf.Bytes(), 0o644))
-
-	chk, err := mfer.NewChecker("/d/index.mf", "/d", fs)
-	require.NoError(t, err)
-	require.False(t, chk.IsSigned())
-
-	return chk
 }
 
-func TestNoManifestFoundMessage(t *testing.T) {
+// TestErrorMessagesVerbatim pins the exact rendered text of the CLI's
-	t.Parallel()
+// user-visible error messages.
-
-	_, err := findManifest(afero.NewMemMapFs(), "/tmp/x")
-	require.ErrorIs(t, err, errNoManifestFound)
-	assert.EqualError(t, err,
-		"no manifest found in /tmp/x (looked for index.mf and .index.mf)")
-}
-
-func TestVerifyRequiredSignerMessages(t *testing.T) {
-	t.Parallel()
-
-	t.Run("invalid fingerprint length", func(t *testing.T) {
-		t.Parallel()
-
-		err := verifyRequiredSigner(unsignedChecker(t), "12345678")
-		require.ErrorIs(t, err, errInvalidFingerprint)
-		assert.EqualError(t, err,
-			"invalid fingerprint: must be exactly 40 hex characters, got 8")
-	})
-
-	t.Run("manifest not signed", func(t *testing.T) {
-		t.Parallel()
-
-		err := verifyRequiredSigner(unsignedChecker(t), msgFpA)
-		require.ErrorIs(t, err, errManifestNotSigned)
-		assert.EqualError(t, err,
-			"manifest is not signed, but signature from "+msgFpA+" is required")
-	})
-}
-
-// TestSignerMismatchMessage drives verifyRequiredSigner against a real signed
-// manifest. The embedded fingerprint is whatever the generated key produced,
-// so it is read back from the checker and substituted into the expected
-// string; the required signer is a fixed value that cannot match it. Requires
-// gpg and is skipped where it is absent, as the other signing tests are.
 //
-//nolint:paralleltest // signedChecker calls t.Setenv, which bars t.Parallel
+// These strings are an interface: they are grepped for in CI pipelines
-func TestSignerMismatchMessage(t *testing.T) {
+// and quoted in bug reports. The messages are assembled by wrapping
-	chk := signedChecker(t)
+// static sentinels, and it is easy to change what a user sees while
-
+// only meaning to make an error matchable with errors.Is - which is
-	embeddedFP, err := chk.ExtractEmbeddedSigningKeyFP()
+// precisely what happened once already. Any change to a string below is
-	require.NoError(t, err)
+// therefore a deliberate, separately stated change, never a side effect
-
+// of a refactor.
-	err = verifyRequiredSigner(chk, msgFpB)
+func TestErrorMessagesVerbatim(t *testing.T) {
-	require.ErrorIs(t, err, errSignerMismatch)
-	assert.EqualError(t, err,
-		"embedded signing key fingerprint "+embeddedFP+
-			" does not match required "+msgFpB)
-}
-
-// signedChecker builds a Checker over a manifest signed by a throwaway GPG
-// key generated in a temporary GNUPGHOME.
-func signedChecker(t *testing.T) *mfer.Checker {
-	t.Helper()
-
-	_, err := exec.LookPath("gpg")
-	if err != nil {
-		t.Skip("gpg not installed, skipping signing test")
-	}
-
-	gpgHome := t.TempDir()
-	params := "%no-protection\n" +
-		"Key-Type: RSA\nKey-Length: 2048\n" +
-		"Name-Real: MFER Test Key\nName-Email: test@mfer.test\n" +
-		"Expire-Date: 0\n%commit\n"
-	paramsFile := filepath.Join(gpgHome, "key-params")
-	require.NoError(t, os.WriteFile(paramsFile, []byte(params), 0o600))
-
-	//nolint:gosec // paramsFile is a test-controlled path inside t.TempDir()
-	cmd := exec.CommandContext(context.Background(), "gpg",
-		"--batch", "--gen-key", paramsFile)
-	cmd.Env = append(os.Environ(), "GNUPGHOME="+gpgHome)
-
-	out, err := cmd.CombinedOutput()
-	if err != nil {
-		t.Skipf("failed to generate test GPG key: %v: %s", err, out)
-	}
-
-	t.Setenv("GNUPGHOME", gpgHome)
-
-	b := mfer.NewBuilder()
-	b.SetSigningOptions(&mfer.SigningOptions{KeyID: mfer.GPGKeyID("test@mfer.test")})
-
-	content := []byte("signed file")
-	_, err = b.AddFile("f.txt", mfer.FileSize(len(content)), mfer.ModTime{},
-		bytes.NewReader(content), nil)
-	require.NoError(t, err)
-
-	var buf bytes.Buffer
-
-	require.NoError(t, b.Build(&buf))
-
-	fs := afero.NewMemMapFs()
-	require.NoError(t, afero.WriteFile(fs, "/index.mf", buf.Bytes(), 0o644))
-
-	chk, err := mfer.NewChecker("/index.mf", "/", fs)
-	require.NoError(t, err)
-	require.True(t, chk.IsSigned())
-
-	return chk
-}
-
-func TestPathDoesNotExistMessage(t *testing.T) {
 	t.Parallel()
 
-	set := flag.NewFlagSet("gen", flag.ContinueOnError)
+	checkErrMsgCases(t, []errMsgCase{
-	require.NoError(t, set.Parse([]string{"nope"}))
+		{
-
+			name: "check: no manifest found",
-	mfa := &CLIApp{Fs: afero.NewMemMapFs()}
+			err: fmt.Errorf("%w in %s (looked for index.mf and .index.mf)",
-	ctx := urfcli.NewContext(nil, set, nil)
+				errNoManifestFound, "/tmp/x"),
-
+			want: "no manifest found in /tmp/x " +
-	_, err := mfa.collectInputPaths(ctx.Args())
+				"(looked for index.mf and .index.mf)",
-	require.ErrorIs(t, err, errPathNotExist)
+		},
-	assert.EqualError(t, err, "path does not exist: nope")
+		{
-}
+			name: "check: invalid fingerprint length",
-
+			err:  fmt.Errorf("%w, got %d", errInvalidFingerprint, 8),
-func TestOutputFileExistsMessage(t *testing.T) {
+			want: "invalid fingerprint: must be exactly 40 hex characters, got 8",
-	t.Parallel()
+		},
-
+		{
-	fs := afero.NewMemMapFs()
+			name: "check: manifest not signed",
-	require.NoError(t, fs.MkdirAll("/d", 0o755))
+			err: fmt.Errorf("%w, but signature from %s is required",
-	require.NoError(t, afero.WriteFile(fs, "/d/f.txt", []byte("hi"), 0o644))
+				errManifestNotSigned, msgFpA),
-	require.NoError(t, afero.WriteFile(fs, "/out.mf", []byte("old"), 0o644))
+			want: "manifest is not signed, but signature from " + msgFpA +
-
+				" is required",
-	set := flag.NewFlagSet("gen", flag.ContinueOnError)
+		},
-	set.String("output", "", "")
+		{
-	set.Bool("force", false, "")
+			name: "check: signer mismatch",
-	require.NoError(t, set.Parse([]string{"/d"}))
+			err: fmt.Errorf("embedded signing key fingerprint %s %w %s",
-	require.NoError(t, set.Set("output", "/out.mf"))
+				msgFpA, errSignerMismatch, msgFpB),
-
+			want: "embedded signing key fingerprint " + msgFpA +
-	mfa := &CLIApp{Fs: fs}
+				" does not match required " + msgFpB,
-	ctx := urfcli.NewContext(nil, set, nil)
+		},
-
+		{
-	// generateManifestOperation writes to the process-global logger during
+			name: "gen: path does not exist",
-	// enumeration, so serialize with the other CLI runs.
+			err:  fmt.Errorf("%w: %s", errPathNotExist, "nope"),
-	err := runLocked(func() error { return mfa.generateManifestOperation(ctx) })
+			want: "path does not exist: nope",
-	require.ErrorIs(t, err, errOutputExists)
+		},
-	assert.EqualError(t, err,
+		{
-		"output file /out.mf already exists (use --force to overwrite)")
+			name: "gen: output file exists",
-}
+			err:  fmt.Errorf("output file %s %w", "index.mf", errOutputExists),
-
+			want: "output file index.mf already exists " +
-func TestManifestLoaderHTTPStatusMessage(t *testing.T) {
+				"(use --force to overwrite)",
-	t.Parallel()
+		},
-
+		{
-	server := httptest.NewServer(
+			name: "mfer: unknown command",
-		http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+			err:  fmt.Errorf("%w %q", errUnknownCommand, "bogus"),
-			w.WriteHeader(http.StatusNotFound)
+			want: `unknown command "bogus"`,
-		}))
+		},
-	defer server.Close()
-
-	mfa := &CLIApp{Fs: afero.NewMemMapFs()}
-
-	_, err := mfa.openManifestReader(server.URL + "/foo.mf")
-	require.ErrorIs(t, err, errHTTPStatus)
-	assert.EqualError(t, err,
-		"failed to fetch "+server.URL+"/foo.mf: HTTP 404")
-}
-
-func TestFetchManifestHTTPStatusMessage(t *testing.T) {
-	t.Parallel()
-
-	server := httptest.NewServer(
-		http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-			w.WriteHeader(http.StatusNotFound)
-		}))
-	defer server.Close()
-
-	set := flag.NewFlagSet("fetch", flag.ContinueOnError)
-	require.NoError(t, set.Parse([]string{server.URL}))
-
-	mfa := &CLIApp{Fs: afero.NewMemMapFs()}
-	ctx := urfcli.NewContext(nil, set, nil)
-
-	// fetchManifestOperation logs to the process-global logger.
-	err := runLocked(func() error { return mfa.fetchManifestOperation(ctx) })
-	require.ErrorIs(t, err, errHTTPStatus)
-	assert.EqualError(t, err, "failed to fetch manifest: HTTP 404")
-}
-
-func TestFetchFileHTTPStatusMessage(t *testing.T) {
-	t.Parallel()
-
-	server := httptest.NewServer(
-		http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-			w.WriteHeader(http.StatusInternalServerError)
-		}))
-	defer server.Close()
-
-	err := downloadFile(context.Background(), server.URL+"/x", "x",
-		&mfer.MFFilePath{}, nil)
-	require.ErrorIs(t, err, errHTTPStatus)
-	assert.EqualError(t, err, "HTTP 500")
-}
-
-func TestURLRequiredMessage(t *testing.T) {
-	t.Parallel()
-
-	set := flag.NewFlagSet("fetch", flag.ContinueOnError)
-	require.NoError(t, set.Parse([]string{}))
-
-	mfa := &CLIApp{Fs: afero.NewMemMapFs()}
-	ctx := urfcli.NewContext(nil, set, nil)
-
-	// fetchManifestOperation logs to the process-global logger.
-	err := runLocked(func() error { return mfa.fetchManifestOperation(ctx) })
-	require.ErrorIs(t, err, errURLRequired)
-	assert.EqualError(t, err, "URL argument required")
-}
-
-func TestSanitizePathMessages(t *testing.T) {
-	t.Parallel()
-
-	t.Run("empty", func(t *testing.T) {
-		t.Parallel()
-
-		_, err := sanitizePath("")
-		require.ErrorIs(t, err, errEmptyPath)
-		assert.EqualError(t, err, "empty path")
-	})
-
-	t.Run("absolute", func(t *testing.T) {
-		t.Parallel()
-
-		_, err := sanitizePath("/etc/passwd")
-		require.ErrorIs(t, err, errAbsolutePath)
-		assert.EqualError(t, err, "absolute path not allowed: /etc/passwd")
-	})
-
-	t.Run("traversal", func(t *testing.T) {
-		t.Parallel()
-
-		_, err := sanitizePath("../x")
-		require.ErrorIs(t, err, errPathTraversal)
-		assert.EqualError(t, err, "path traversal not allowed: ../x")
 	})
 }
 
-func TestSizeMismatchMessage(t *testing.T) {
+// TestFetchErrorMessagesVerbatim pins the fetch and manifest-loader
+// messages; see TestErrorMessagesVerbatim for why.
+func TestFetchErrorMessagesVerbatim(t *testing.T) {
 	t.Parallel()
 
-	// finishDownload returns the size-mismatch error before it touches the
+	checkErrMsgCases(t, []errMsgCase{
-	// paths, digest, or entry, so those can be zero here.
+		{
-	err := finishDownload("", "", 9, 10, nil, nil, nil, nil)
+			name: "manifest_loader: http status",
-	require.ErrorIs(t, err, errSizeMismatch)
+			err: fmt.Errorf("failed to fetch %s: %w %d",
-	assert.EqualError(t, err, "size mismatch: expected 10 bytes, got 9")
+				"https://example.com/index.mf", errHTTPStatus, 404),
+			want: "failed to fetch https://example.com/index.mf: HTTP 404",
+		},
+		{
+			name: "fetch: manifest http status",
+			err: fmt.Errorf("failed to fetch manifest: %w %d",
+				errHTTPStatus, 404),
+			want: "failed to fetch manifest: HTTP 404",
+		},
+		{
+			name: "fetch: file http status",
+			err:  fmt.Errorf("%w %d", errHTTPStatus, 500),
+			want: "HTTP 500",
+		},
+		{
+			name: "fetch: empty path",
+			err:  errEmptyPath,
+			want: "empty path",
+		},
+		{
+			name: "fetch: absolute path",
+			err:  fmt.Errorf("%w: %s", errAbsolutePath, "/etc/passwd"),
+			want: "absolute path not allowed: /etc/passwd",
+		},
+		{
+			name: "fetch: path traversal",
+			err:  fmt.Errorf("%w: %s", errPathTraversal, "../x"),
+			want: "path traversal not allowed: ../x",
+		},
+		{
+			name: "fetch: size mismatch",
+			err: fmt.Errorf("%w: expected %d bytes, got %d",
+				errSizeMismatch, 10, 9),
+			want: "size mismatch: expected 10 bytes, got 9",
+		},
+		{
+			name: "fetch: url required",
+			err:  errURLRequired,
+			want: "URL argument required",
+		},
+		{
+			name: "fetch: hash mismatch",
+			err:  errHashMismatch,
+			want: "hash mismatch",
+		},
+	})
 }
 
-func TestHashMismatchMessage(t *testing.T) {
+// TestSentinelsAreMatchable checks that the wrapped forms of the
+// messages above remain matchable with errors.Is, which is the reason
+// the sentinels exist at all.
+func TestSentinelsAreMatchable(t *testing.T) {
 	t.Parallel()
 
-	// A 32-byte digest that matches none of the (empty) manifest hashes.
+	wrapped := fmt.Errorf("embedded signing key fingerprint %s %w %s",
-	err := verifyDownloadedHash(make([]byte, 32), &mfer.MFFilePath{})
+		"a", errSignerMismatch, "b")
-	require.ErrorIs(t, err, errHashMismatch)
+	require.ErrorIs(t, wrapped, errSignerMismatch)
-	require.NotErrorIs(t, err, errSizeMismatch)
+
-	assert.EqualError(t, err, "hash mismatch")
+	wrapped = fmt.Errorf("output file %s %w", "index.mf", errOutputExists)
+	require.ErrorIs(t, wrapped, errOutputExists)
+
+	wrapped = fmt.Errorf("failed to fetch manifest: %w %d", errHTTPStatus, 404)
+	require.ErrorIs(t, wrapped, errHTTPStatus)
+
+	assert.NotErrorIs(t, errHashMismatch, errSizeMismatch)
 }

internal/cli/freshen_test.go

@@ -110,10 +110,7 @@ func TestFreshenRecordEntryMtimePresence(t *testing.T) {
 
 	const relPath = "file1.txt"
 
-	// The scanned file's mtime is the Unix epoch. If recordEntry ever misreads
+	mtime := time.Unix(1_700_000_000, 0)
-	// an absent manifest mtime as the epoch, the "absent" case below would
-	// compare equal to this and be classified unchanged, so the test fails.
-	mtime := time.Unix(0, 0)
 	info := stubFileInfo{size: 8, mtime: mtime}
 
 	for _, tc := range []struct {

mfer/checker.go

@@ -312,6 +312,10 @@ func (c *Checker) FindExtraFiles(ctx context.Context, results chan<- Result) err
 }
 
 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())
 	relPath := RelFilePath(entry.GetPath())
 

mfer/deserialize.go

@@ -25,6 +25,7 @@ var (
 	errDecompressedTooLarge = errors.New("decompressed data exceeds maximum allowed size")
 	errUUIDMismatch         = errors.New("outer and inner UUID mismatch")
 	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).
@@ -181,6 +182,19 @@ func (m *manifest) deserializeInner() error {
 		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()))
 
 	return nil

mfer/deserialize_path_test.go

@@ -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")
+}