Refuse credentials in a storage URL's endpoint or rclone remote name (closes #322)

storage_url refused only the outer URL's userinfo and unknown query
parameters. Userinfo inside the s3 endpoint= value, and rclone's
remote,param=value parameters in the remote name, were accepted and
then printed by info, remote info and snapshot create. Both are now
refused when the storage URL is parsed, without echoing the value: a
host name never contains "@", and an rclone remote name never contains
a comma. The rclone case has its own error pointing at rclone config,
since the existing credentials error names the s3.* keys.

Model: opus-5-5

internal/snapshot/exclude_test.go

@@ -531,3 +531,50 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"Unanchored pattern for file should match anywhere")
 }
+
+func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/projectname should exclude BOTH:
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 2
+	require.Equal(t, 2, result.FilesScanned,
+		"**/ directory pattern should match at the top level and nested")
+}
+
+func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
+	t.Parallel()
+
+	// As in gitignore, a leading **/ also matches directly under the source dir
+	fs := setupAnchoredTestFS(t)
+
+	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
+	defer cleanup()
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
+	require.NoError(t, err)
+
+	// **/*.txt should exclude ALL .txt files:
+	// - /backup/file.txt
+	// - /backup/projectname/file.txt
+	// - /backup/otherproject/projectname/file.txt
+	// Total files: 4, excluded: 3
+	require.Equal(t, 1, result.FilesScanned,
+		"**/ file pattern should match at the top level and nested")
+}

internal/snapshot/scanner.go

@@ -2018,6 +2018,14 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		// Remove trailing slash if present (directory indicator)
 		pattern = strings.TrimSuffix(pattern, "/")
 
+		// A leading "**/" demands a "/" before the name and so misses an
+		// entry directly under the source path. An unanchored pattern
+		// already matches at every depth, so drop the prefix: as in
+		// gitignore, "**/x" then also matches a top-level "x".
+		if !anchored {
+			pattern = strings.TrimPrefix(pattern, "**/")
+		}
+
 		// Compile the glob pattern
 		// For patterns without path separators, we need to match them as components
 		// e.g., ".git" should match ".git" anywhere in the path

internal/storage/url.go

@@ -29,7 +29,10 @@ var (
 	ErrURLCredentials     = errors.New(
 		"storage URL must not carry credentials; " +
 			"set s3.access_key_id and s3.secret_access_key in the config instead")
-	ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
+	ErrURLUnknownParam    = errors.New("unknown query parameter in storage URL")
+	ErrRcloneRemoteParams = errors.New(
+		"rclone URL must not carry parameters in the remote name; " +
+			"set them on the remote with rclone config instead")
 )
 
 // URL represents a parsed storage URL.
@@ -90,8 +93,9 @@ func parseFileURL(rawPath string) (*URL, error) {
 }
 
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
-// the userinfo and any query parameter other than endpoint, region and
-// ssl, so a credential-bearing URL is never stored or echoed.
+// the userinfo or in the endpoint parameter's userinfo, and any query
+// parameter other than endpoint, region and ssl, so a credential-bearing
+// URL is never stored or echoed.
 func parseS3URL(rawURL string) (*URL, error) {
 	u, err := url.Parse(rawURL)
 	if err != nil {
@@ -114,6 +118,14 @@ func parseS3URL(rawURL string) (*URL, error) {
 		return nil, err
 	}
 
+	// A host name never contains "@", so one in an endpoint, with or
+	// without a scheme, can only introduce userinfo.
+	for _, endpoint := range query["endpoint"] {
+		if strings.Contains(endpoint, "@") {
+			return nil, ErrURLCredentials
+		}
+	}
+
 	return &URL{
 		Scheme:   schemeS3,
 		Bucket:   bucket,
@@ -125,8 +137,9 @@ func parseS3URL(rawURL string) (*URL, error) {
 }
 
 // parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
-// query parameters, so credentials in the userinfo and any parameter at
-// all are rejected rather than silently ignored.
+// query parameters, so credentials in the userinfo, parameters in the
+// remote name and any query parameter at all are rejected rather than
+// silently ignored.
 func parseRcloneURL(rawURL string) (*URL, error) {
 	u, err := url.Parse(rawURL)
 	if err != nil {
@@ -142,6 +155,12 @@ func parseRcloneURL(rawURL string) (*URL, error) {
 		return nil, ErrMissingRemote
 	}
 
+	// An rclone remote name never contains a comma; one starts rclone's
+	// remote,param=value form, whose values can be credentials.
+	if strings.Contains(remote, ",") {
+		return nil, ErrRcloneRemoteParams
+	}
+
 	err = rejectUnknownParams(u.Query())
 	if err != nil {
 		return nil, err

internal/storage/url_parse_test.go

@@ -150,6 +150,19 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 			wantErr: storage.ErrURLCredentials,
 			secrets: []string{key, secret, "mybucket"},
 		},
+		{
+			name: "s3 userinfo in endpoint",
+			raw: "s3://mybucket?endpoint=https://" +
+				key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
+		{
+			name:    "s3 userinfo in endpoint without scheme",
+			raw:     "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
 		{
 			name:    "s3 unknown query param",
 			raw:     "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -203,6 +216,27 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 	}
 }
 
+// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
+// remote name carrying parameters (rclone's "remote,param=value" form,
+// which can hold a credential) is rejected without echoing the value.
+func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
+	t.Parallel()
+
+	const secret = "topsecret"
+
+	raw := "rclone://gdrive,client_secret=" + secret + "/backups"
+
+	_, err := storage.ParseStorageURL(raw)
+	if !errors.Is(err, storage.ErrRcloneRemoteParams) {
+		t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
+			raw, err, storage.ErrRcloneRemoteParams)
+	}
+
+	if strings.Contains(err.Error(), secret) {
+		t.Errorf("error message leaked %q: %v", secret, err.Error())
+	}
+}
+
 // TestParseStorageURLParseFailureHidesURL checks that when url.Parse
 // itself fails, the wrapped error carries only the inner cause, not the
 // *url.Error whose text embeds the raw (possibly credential-bearing) URL.

internal/vaultik/blob_fetch.go

@@ -103,8 +103,6 @@ func (v *Vaultik) FetchAndDecryptBlob(
 }
 
 // FetchBlob downloads a blob and returns a reader for the encrypted data.
-// The reader is closed as soon as ctx is cancelled, which ends a read
-// blocked inside it.
 func (v *Vaultik) FetchBlob(
 	ctx context.Context, blobHash string,
 ) (io.ReadCloser, error) {
@@ -122,47 +120,5 @@ func (v *Vaultik) FetchBlob(
 		return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
 	}
 
-	return newCloseOnCancelReader(ctx, rc), nil
-}
-
-// closeOnCancelReader closes the reader it wraps when ctx is cancelled.
-// Not every backend's reader stops on cancel by itself (the file
-// backend's does not), and a read stalled on a slow or hung source would
-// otherwise outlast the shutdown timeout, so the process would exit
-// before restore or deep verify removed its decrypted temporary files.
-type closeOnCancelReader struct {
-	io.ReadCloser
-
-	ctx  context.Context //nolint:containedctx // Read reports its error
-	stop func() bool
-}
-
-func newCloseOnCancelReader(
-	ctx context.Context, rc io.ReadCloser,
-) *closeOnCancelReader {
-	return &closeOnCancelReader{
-		ReadCloser: rc,
-		ctx:        ctx,
-		stop:       context.AfterFunc(ctx, func() { _ = rc.Close() }),
-	}
-}
-
-// Read returns the context's error, not the closed reader's, once ctx
-// has been cancelled.
-func (r *closeOnCancelReader) Read(p []byte) (int, error) {
-	n, err := r.ReadCloser.Read(p)
-	if err != nil && r.ctx.Err() != nil {
-		return n, r.ctx.Err()
-	}
-
-	return n, err
-}
-
-// Close closes the wrapped reader, unless the cancel already closed it.
-func (r *closeOnCancelReader) Close() error {
-	if !r.stop() {
-		return nil
-	}
-
-	return r.ReadCloser.Close()
+	return rc, nil
 }

internal/vaultik/restore_interrupt_test.go

@@ -142,14 +142,14 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
 }
 
 // scratchEntries returns the vaultik blob-cache and snapshot-database
-// scratch entries (restore's and deep verify's) currently present in dir.
+// scratch entries currently present in dir.
 func scratchEntries(t *testing.T, dir string) []string {
 	t.Helper()
 
 	var matches []string
 
 	for _, pattern := range []string{
-		"vaultik-blobcache-*", "vaultik-restore-*", "vaultik-verify-*",
+		"vaultik-blobcache-*", "vaultik-restore-*",
 	} {
 		found, err := filepath.Glob(filepath.Join(dir, pattern))
 		require.NoError(t, err)
@@ -206,119 +206,3 @@ func TestRestoreSkipErrorsCancelDuringBlobDownload(t *testing.T) {
 	assert.NotContains(t, out.String(), srcPath,
 		"the cancel was reported as a failed file")
 }
-
-// stallingBlobStorer wraps a Storer so that every blob download hands
-// over the first half of the blob and then stalls, ignoring the context,
-// as a file:// blob on a hung USB stick or network share does. Only
-// closing the returned reader ends the stall.
-type stallingBlobStorer struct {
-	storage.Storer
-
-	once    sync.Once
-	stalled chan struct{}
-}
-
-func newStallingBlobStorer(inner storage.Storer) *stallingBlobStorer {
-	return &stallingBlobStorer{Storer: inner, stalled: make(chan struct{})}
-}
-
-func (s *stallingBlobStorer) Get(
-	ctx context.Context, key string,
-) (io.ReadCloser, error) {
-	rc, err := s.Storer.Get(ctx, key)
-	if err != nil || !strings.HasPrefix(key, "blobs/") {
-		return rc, err
-	}
-
-	blob, err := io.ReadAll(rc)
-	_ = rc.Close()
-
-	if err != nil {
-		return nil, err
-	}
-
-	// The writer is never closed, so once the first half has been read
-	// the next Read blocks until the reader is closed.
-	pr, pw := io.Pipe()
-
-	go func() {
-		_, _ = pw.Write(blob[:len(blob)/2])
-
-		s.once.Do(func() { close(s.stalled) })
-	}()
-
-	return pr, nil
-}
-
-// TestInterruptDuringStalledBlobReadCleansTempDir stops a restore and a
-// deep verify while a blob read is stalled on a source that ignores the
-// context. Stopping must end that read, so the operation unwinds and
-// removes its decrypted scratch files well within the shutdown timeout
-// (issue #325).
-//
-// Not parallel: it points TMPDIR at a private directory (via t.Setenv)
-// so it can assert on exactly the scratch files the operation created.
-func TestInterruptDuringStalledBlobReadCleansTempDir(t *testing.T) {
-	log.Initialize(log.Config{})
-
-	operations := map[string]func(v *Vaultik, snapshotID, targetDir string) error{
-		"restore": func(v *Vaultik, snapshotID, targetDir string) error {
-			return v.Restore(&RestoreOptions{
-				SnapshotID: snapshotID,
-				TargetDir:  targetDir,
-			})
-		},
-		"deep verify": func(v *Vaultik, snapshotID, _ string) error {
-			return v.RunDeepVerify(snapshotID, &VerifyOptions{Deep: true})
-		},
-	}
-
-	for name, op := range operations {
-		t.Run(name, func(t *testing.T) {
-			fs := afero.NewOsFs()
-			root := t.TempDir()
-
-			// Random content, so the blob stays large enough to stall
-			// part-way through its compressed, encrypted body.
-			cfg, storer, snapshotID, _ := backupOneFile(context.Background(),
-				t, fs, root, "a.bin", randomBytes(t, 256*1024), 0o644)
-
-			scratch := filepath.Join(root, "scratch")
-			require.NoError(t, fs.MkdirAll(scratch, 0o755))
-			t.Setenv("TMPDIR", scratch)
-
-			stalling := newStallingBlobStorer(storer)
-
-			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
-
-			v := newRestoreVaultik(ctx, cfg, stalling, fs)
-			v.cancel = cancel
-
-			var opErr error
-
-			stop := v.StartOperation(func() {
-				opErr = op(v, snapshotID, filepath.Join(root, "restored"))
-			})
-
-			select {
-			case <-stalling.stalled:
-			case <-time.After(30 * time.Second):
-				t.Fatal("the operation never reached a blob read")
-			}
-
-			require.NotEmpty(t, scratchEntries(t, scratch),
-				"expected decrypted scratch files to exist mid-read")
-
-			stopCtx, stopCancel := context.WithTimeout(
-				context.Background(), 10*time.Second)
-			defer stopCancel()
-
-			require.True(t, stop(stopCtx),
-				"stop timed out; the stalled blob read was not interrupted")
-			require.ErrorIs(t, opErr, context.Canceled)
-			require.Empty(t, scratchEntries(t, scratch),
-				"decrypted scratch files remained after the interrupt")
-		})
-	}
-}