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 without echoing the value: a host name never contains "@", and
an rclone remote name never contains a comma. An s3 query that cannot
be decoded (a ";" or a bad "%" escape) is refused too, because decoding
drops that part, endpoint included, before it can be checked. The comma
is checked before url.Parse, whose error for such a name prints part of
it. The rclone case has its own error pointing at rclone config.

Model: opus-5-5

README.md

@@ -351,20 +351,16 @@ snapshot from the local index and strips the snapshot's metadata from
 the backup destination store. Blobs are NOT touched — deleting blobs
 requires reading every remaining remote manifest (the destination store
 may hold snapshots this host doesn't know about), which is what
-`vaultik prune` does. The command prints the `vaultik prune` invocation
-to run as a follow-up only when it removed the snapshot's metadata from
-the destination store, and never under `--json`. An ID that names no
-snapshot in the local index or on the destination store is an error;
-with `--local-only`, the snapshot must be in the local index. Local row
+`vaultik prune` does. On success the command prints the exact `vaultik
+prune` invocation to run as a follow-up. An ID that names no snapshot in
+the local index or on the destination store is an error; with
+`--local-only`, the snapshot must be in the local index. Local row
 cleanup (files, chunks, blobs the snapshot was the last referrer for)
-runs automatically. If removing the snapshot's metadata from the
-destination store fails (for example because the store is unreachable),
-the local-DB removal still completes and a warning is emitted; run
-`vaultik snapshot remove <snapshot-id>` again once the store is reachable
-to remove the snapshot's metadata from it (`vaultik prune` does not). For
-a snapshot that is only on the destination store, that failure is an
-error. To wipe everything on the destination in one go, use `vaultik
-remote nuke --force`.
+runs automatically. If the destination store is unreachable, the local-DB
+removal still completes and a warning is emitted; run `vaultik snapshot
+remove <snapshot-id>` again once the store is reachable to remove the
+snapshot's metadata from it (`vaultik prune` does not). To wipe everything
+on the destination in one go, use `vaultik remote nuke --force`.
 * `--local-only`: Skip remote cleanup; only touch the local index
 * `--dry-run`: Show what would be deleted without deleting
 * `--force`: Skip confirmation prompt

internal/cli/snapshot.go

@@ -270,9 +270,8 @@ By default, this removes the snapshot from the local index database and
 strips the snapshot's metadata from the backup destination store. Blobs
 are NOT touched: deleting them requires reading every remaining remote
 manifest (the destination store may hold snapshots this host doesn't
-know about), which is what 'vaultik prune' does. The command prints the
-'vaultik prune' invocation to run as a follow-up only when it removed the
-snapshot's metadata from the destination store, and never under --json.
+know about), which is what 'vaultik prune' does. On success the command
+prints the exact 'vaultik prune' invocation to run as a follow-up.
 
 An ID that names no snapshot in the local index or on the destination
 store is an error.
@@ -281,12 +280,10 @@ Use --local-only to skip the remote half (e.g. when you want to forget a
 snapshot locally without touching the destination store); the snapshot
 must then be in the local index.
 
-If removing the snapshot's metadata from the destination store fails (for
-example because the remote is unreachable), the local-database removal
-still completes and a warning is emitted; run 'vaultik snapshot remove
-<snapshot-id>' again once the destination store is reachable to remove
-the snapshot's metadata from it ('vaultik prune' does not). For a
-snapshot that is only on the destination store, that failure is an error.
+If the remote is unreachable, the local-database removal still completes
+and a warning is emitted; run 'vaultik snapshot remove <snapshot-id>' again
+once the destination store is reachable to remove the snapshot's metadata
+from it ('vaultik prune' does not).
 
 To wipe the entire destination store and start over, use 'vaultik remote
 nuke --force' — it is the single supported entry point for that.`,

internal/storage/url.go

@@ -30,6 +30,12 @@ var (
 		"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")
+	ErrURLBadQuery     = errors.New(
+		"storage URL query cannot be decoded; " +
+			"check it for a ; or a % not followed by two hex digits")
+	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 +96,9 @@ 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, a query that
+// cannot be decoded, 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 {
@@ -107,13 +114,26 @@ func parseS3URL(rawURL string) (*URL, error) {
 		return nil, ErrMissingBucket
 	}
 
-	query := u.Query()
+	// u.Query() would silently drop a part it cannot decode, endpoint
+	// included. The decode error is not wrapped: it can quote the value.
+	query, err := url.ParseQuery(u.RawQuery)
+	if err != nil {
+		return nil, ErrURLBadQuery
+	}
 
 	err = rejectUnknownParams(query, "endpoint", "region", "ssl")
 	if err != nil {
 		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,
@@ -125,9 +145,23 @@ 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) {
+	// The remote name runs up to the first "/", "?" or "#". It never
+	// contains a comma; one starts rclone's remote,param=value form,
+	// whose values can be credentials. This is checked before url.Parse,
+	// whose error for such a name can print part of it.
+	remote := strings.TrimPrefix(rawURL, "rclone://")
+	if end := strings.IndexAny(remote, "/?#"); end >= 0 {
+		remote = remote[:end]
+	}
+
+	if strings.Contains(remote, ",") {
+		return nil, ErrRcloneRemoteParams
+	}
+
 	u, err := url.Parse(rawURL)
 	if err != nil {
 		return nil, wrapParseError(err)
@@ -137,7 +171,7 @@ func parseRcloneURL(rawURL string) (*URL, error) {
 		return nil, ErrURLCredentials
 	}
 
-	remote := u.Host
+	remote = u.Host
 	if remote == "" {
 		return nil, ErrMissingRemote
 	}

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 +216,104 @@ 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,
+// including the URLs that url.Parse itself refuses.
+func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name    string
+		raw     string
+		secrets []string // must not appear in the error message
+	}{
+		{
+			name:    "configured remote",
+			raw:     "rclone://gdrive,client_secret=topsecret/backups",
+			secrets: []string{"topsecret"},
+		},
+		{
+			name:    "remote defined inline",
+			raw:     "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
+			secrets: []string{"KEY", "SECRET"},
+		},
+		{
+			name:    "colon in a parameter value",
+			raw:     "rclone://gdrive,client_secret=ab:cd/backups",
+			secrets: []string{"cd"},
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if !errors.Is(err, storage.ErrRcloneRemoteParams) {
+				t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrRcloneRemoteParams)
+			}
+
+			for _, secret := range tc.secrets {
+				if strings.Contains(err.Error(), secret) {
+					t.Errorf("error message leaked %q: %v", secret, err.Error())
+				}
+			}
+		})
+	}
+}
+
+// TestParseStorageURLRejectsUndecodableQuery checks that an s3 URL whose
+// query cannot be decoded is rejected, not read with that part of the
+// query left out, and that the error does not echo it.
+func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
+	t.Parallel()
+
+	const (
+		key    = "AKIAKEY"
+		secret = "topsecret"
+	)
+
+	cases := []struct {
+		name string
+		raw  string
+	}{
+		{
+			name: "semicolon",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"@minio.example.com:9000;region=us-east-1",
+		},
+		{
+			name: "bad percent escape",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"%zz@minio.example.com:9000",
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if err == nil {
+				t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
+			}
+
+			if !errors.Is(err, storage.ErrURLBadQuery) {
+				t.Errorf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrURLBadQuery)
+			}
+
+			for _, s := range []string{key, secret, "minio.example.com"} {
+				if strings.Contains(err.Error(), s) {
+					t.Errorf("error message leaked %q: %v", s, 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/remove_snapshot_test.go

@@ -17,7 +17,6 @@ import (
 	"sneak.berlin/go/vaultik/internal/log"
 	"sneak.berlin/go/vaultik/internal/snapshot"
 	"sneak.berlin/go/vaultik/internal/storage"
-	"sneak.berlin/go/vaultik/internal/storage/faultstore"
 	"sneak.berlin/go/vaultik/internal/types"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
@@ -432,40 +431,6 @@ func TestRemoveSnapshot_NotInLocalIndex(t *testing.T) {
 	assert.Contains(t, out, "Removed snapshot metadata from remote storage")
 }
 
-// TestRemoveSnapshot_NotInLocalIndexDeleteFails checks that removing a
-// snapshot only the destination store holds fails when its metadata
-// cannot be deleted there, under --force and under --json: nothing was
-// removed, so the command must not succeed.
-func TestRemoveSnapshot_NotInLocalIndexDeleteFails(t *testing.T) {
-	log.Initialize(log.Config{})
-	t.Parallel()
-
-	for name, opts := range map[string]vaultik.RemoveOptions{
-		"force": {Force: true},
-		"json":  {JSON: true},
-	} {
-		t.Run(name, func(t *testing.T) {
-			t.Parallel()
-
-			store := newTestStorer()
-			addManifest(t, store, "snapshot-001", nil)
-
-			faulty := faultstore.New(store)
-			faulty.OnDelete = func(string) bool { return true }
-
-			tv := vaultik.NewForTesting(faulty)
-			tv.Repositories = newLocalIndex(t)
-
-			result, err := tv.RemoveSnapshot("snapshot-001", &opts)
-
-			require.ErrorIs(t, err, faultstore.ErrInjectedDelete)
-			assert.False(t, result.RemoteRemoved)
-			assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
-			assert.Empty(t, tv.Stdout.String())
-		})
-	}
-}
-
 func TestRemoveAllSnapshots_RequiresForce(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()

internal/vaultik/snapshot.go

@@ -1218,11 +1218,9 @@ const snapshotRemoveCommandHint = "vaultik snapshot remove"
 // destination store. Blobs are NOT touched: removing a snapshot's
 // blobs requires reading every remaining remote manifest (the remote
 // may hold snapshots this host doesn't know about), which is what
-// `vaultik prune` is for — when metadata was removed from the
-// destination store, the text output names the prune invocation to run
-// as a follow-up. When removing the metadata fails, a snapshot in the
-// local index is still removed from it, with a warning; a snapshot
-// only on the destination store is an error.
+// `vaultik prune` is for — the command prints the prune invocation to
+// run as a follow-up. When the remote is unreachable the command still
+// completes the local-DB removal and warns.
 func (v *Vaultik) RemoveSnapshot(
 	snapshotID string, opts *RemoveOptions,
 ) (*RemoveResult, error) {
@@ -1258,11 +1256,7 @@ func (v *Vaultik) RemoveSnapshot(
 	}
 
 	if !opts.LocalOnly {
-		result.RemoteRemoved, err = v.removeSnapshotRemote(
-			snapshotID, inLocalIndex, opts)
-		if err != nil {
-			return result, err
-		}
+		result.RemoteRemoved = v.removeSnapshotRemote(snapshotID, opts)
 	}
 
 	if v.SnapshotManager != nil {
@@ -1384,27 +1378,19 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
 }
 
 // removeSnapshotRemote strips the snapshot's metadata from the
-// destination store and returns true when it deleted something. When
-// the snapshot is only on the destination store, a failure is returned
-// as an error, because that removal is all the command does. When the
-// snapshot was in the local index, its removal there has already
-// happened, so a failure is only a warning telling the user to run
-// `vaultik snapshot remove` for the snapshot again once the destination
-// store is reachable (`vaultik prune` never removes snapshot metadata).
-func (v *Vaultik) removeSnapshotRemote(
-	snapshotID string, inLocalIndex bool, opts *RemoveOptions,
-) (bool, error) {
+// destination store, warning and proceeding on failure: the local-DB
+// removal has already happened, so the user is told the remote half
+// didn't finish and to run `vaultik snapshot remove` for the snapshot
+// again once the destination store is reachable (`vaultik prune` never
+// removes snapshot metadata). Returns true when the remote removal
+// succeeded and deleted something.
+func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) bool {
 	log.Info("Removing snapshot metadata from remote storage",
 		"snapshot_id", snapshotID)
 
 	remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
 
 	deleted, err := v.deleteRemoteSnapshotByKey(remoteKey)
-	if err != nil && !inLocalIndex {
-		return false, fmt.Errorf(
-			"removing snapshot metadata from destination store: %w", err)
-	}
-
 	if err != nil {
 		log.Warn("Could not remove snapshot metadata from remote storage; "+
 			"run '"+snapshotRemoveCommandHint+"' with the snapshot's ID "+
@@ -1419,10 +1405,10 @@ func (v *Vaultik) removeSnapshotRemote(
 				err, snapshotRemoveCommandHint, snapshotID)
 		}
 
-		return false, nil
+		return false
 	}
 
-	return deleted > 0, nil
+	return deleted > 0
 }
 
 // RemoveAllSnapshots removes every snapshot known to the local