Merge pull request 'refactor(#154): extract baseSubprocessArgs helper in main_test.go subprocess tests' (#155) from issue-154 into main

Reviewed-on: #155
Reviewed-by: security-review-bot <10+security-review-bot@noreply.gitea.weiker.me>
Reviewed-by: Aaron Weiker <aaron@weiker.org>

cmd/review-bot/main_test.go

@@ -903,12 +903,17 @@ func TestMainSubprocess_InvalidRepo(t *testing.T) {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		args := baseSubprocessArgs()
 		// Replace the canonical --repo value with an invalid one.
+		found := false
 		for i, a := range args {
 			if a == "--repo" && i+1 < len(args) {
 				args[i+1] = "invalidrepo"
+				found = true
 				break
 			}
 		}
+		if !found {
+			t.Fatal("baseSubprocessArgs() does not contain --repo; test is broken")
+		}
 		os.Args = args
 		main()
 		return
@@ -930,12 +935,17 @@ func TestMainSubprocess_InvalidPRNumber(t *testing.T) {
 		flag.CommandLine = flag.NewFlagSet(os.Args[0], flag.ExitOnError)
 		args := baseSubprocessArgs()
 		// Replace the canonical --pr value with a non-numeric string.
+		found := false
 		for i, a := range args {
 			if a == "--pr" && i+1 < len(args) {
 				args[i+1] = "notanumber"
+				found = true
 				break
 			}
 		}
+		if !found {
+			t.Fatal("baseSubprocessArgs() does not contain --pr; test is broken")
+		}
 		os.Args = args
 		main()
 		return

cmd/review-bot/validatedocmap.go

@@ -23,19 +23,18 @@ const maxDocmapBytes int64 = 10 * 1024 * 1024 // 10 MB
 //  1. The path resolves to a regular file within resolvedRoot (path
 //     confinement): prevents a PR-controlled --docmap from reading arbitrary
 //     host files via absolute paths or ".." traversal.
-//  2. The resolved path is within resolvedRoot: in-repo file-level symlinks
-//     are allowed when their resolved target is still inside the root;
-//     symlinks that escape the root are rejected by the confinement check.
+//  2. The path is not a symlink: prevents denial-of-service via /dev/zero or
+//     information disclosure via symlinks that point outside the workspace.
 //  3. The file does not exceed maxDocmapBytes: prevents memory exhaustion
 //     from an oversized but legitimately committed doc-map file.
 //
 // resolvedRoot must already be an absolute, symlink-free path (obtained from
 // filepath.Abs + filepath.EvalSymlinks).
-func validateDocmapPath(localPath, resolvedRoot string) (string, error) {
+func validateDocmapPath(localPath, resolvedRoot string) error {
 	// Resolve the docmap path to an absolute path.
 	absPath, err := filepath.Abs(localPath)
 	if err != nil {
-		return "", fmt.Errorf("cannot resolve path: %w", err)
+		return fmt.Errorf("cannot resolve path: %w", err)
 	}
 
 	// Resolve ALL symlink components, not just the final one.
@@ -47,36 +46,41 @@ func validateDocmapPath(localPath, resolvedRoot string) (string, error) {
 	// path is inside the root while the actual destination is not.
 	resolvedPath, err := filepath.EvalSymlinks(absPath)
 	if err != nil {
-		return "", fmt.Errorf("cannot resolve path (symlink): %w", err)
+		return fmt.Errorf("cannot resolve path (symlink): %w", err)
 	}
 
-	// Lstat the resolved path for size and existence checks — EvalSymlinks
-	// guarantees no symlink components remain, so ModeSymlink can never be set.
+	// Lstat the resolved path — at this point resolvedPath is symlink-free, so
+	// ModeSymlink will never be set. We keep the check as defense-in-depth.
 	fi, err := os.Lstat(resolvedPath)
 	if err != nil {
-		return "", fmt.Errorf("cannot stat file: %w", err)
+		return fmt.Errorf("cannot stat file: %w", err)
+	}
+
+	// Defense-in-depth: reject any remaining symlink indicator.
+	if fi.Mode()&os.ModeSymlink != 0 {
+		return fmt.Errorf("symlinks are not allowed")
 	}
 
 	// Reject anything that is not a regular file (directories, FIFOs, device
 	// nodes, etc.) — ParseDocMapConfig expects a plain YAML file and would
 	// produce a confusing error on non-regular entries.
 	if !fi.Mode().IsRegular() {
-		return "", fmt.Errorf("docmap must be a regular file")
+		return fmt.Errorf("docmap must be a regular file")
 	}
 
 	// Confine to resolvedRoot: use the fully-resolved path so that a directory
 	// symlink inside the repo cannot carry the path outside the root.
 	rel, err := filepath.Rel(resolvedRoot, resolvedPath)
 	if err != nil || rel == ".." || strings.HasPrefix(rel, ".."+string(os.PathSeparator)) {
-		return "", fmt.Errorf("path must be within --repo-root")
+		return fmt.Errorf("path must be within --repo-root")
 	}
 
 	// Enforce size cap before reading to prevent memory exhaustion.
 	if fi.Size() > maxDocmapBytes {
-		return "", fmt.Errorf("file size %d bytes exceeds %d-byte limit", fi.Size(), maxDocmapBytes)
+		return fmt.Errorf("file size %d bytes exceeds %d-byte limit", fi.Size(), maxDocmapBytes)
 	}
 
-	return resolvedPath, nil
+	return nil
 }
 
 // runValidateDocmap implements the `review-bot validate-docmap` subcommand.
@@ -140,59 +144,16 @@ func runValidateDocmap(args []string) int {
 	// may reference a PR-controlled file (e.g. .review-bot/doc-map.yml).
 	// Validate that it:
 	//   1. Resolves within resolvedRoot (prevent reading arbitrary host files).
-	//   2. Resolved target stays within the root (in-repo symlinks are allowed
-	//      if they resolve to a path inside the root).
+	//   2. Is not a symlink (prevent /dev/zero or symlink-based host probing).
 	//   3. Does not exceed maxDocmapBytes (prevent memory exhaustion from an
 	//      oversized committed file).
-	// validateDocmapPath returns the resolved path; use it directly to
-	// eliminate any TOCTOU race between validation and use.
-	resolvedDocmap, err := validateDocmapPath(*docmapFlag, resolvedRoot)
-	if err != nil {
+	if err := validateDocmapPath(*docmapFlag, resolvedRoot); err != nil {
 		fmt.Fprintf(errWriter, "Error: --docmap %q is invalid: %v\n", *docmapFlag, err)
 		return 2
 	}
 
-	// Open and read the docmap with a LimitedReader — closes the residual TOCTOU
-	// window between the Lstat size check in validateDocmapPath and the file open
-	// here. The limit is maxDocmapBytes+1 so we can detect a file that grew past
-	// the cap after the stat without reading unbounded bytes.
-	//
-	// Defense-in-depth: stat the path immediately before and after open so we can
-	// detect a file swap between validateDocmapPath's validation and this open via
-	// os.SameFile. An attacker with workspace write access could otherwise replace
-	// the validated file with a symlink in the gap between validation and use.
-	preStat, err := os.Lstat(resolvedDocmap)
-	if err != nil {
-		fmt.Fprintf(errWriter, "Error: failed to stat docmap before open %q: %v\n", *docmapFlag, err)
-		return 2
-	}
-	f, err := os.Open(resolvedDocmap)
-	if err != nil {
-		fmt.Fprintf(errWriter, "Error: failed to open docmap %q: %v\n", *docmapFlag, err)
-		return 2
-	}
-	defer func() { _ = f.Close() }()
-	// Verify we opened the same file that was validated — rejects a swap between
-	// the pre-open Lstat and the open call.
-	postStat, err := f.Stat()
-	if err != nil {
-		fmt.Fprintf(errWriter, "Error: failed to stat open docmap %q: %v\n", *docmapFlag, err)
-		return 2
-	}
-	if !os.SameFile(preStat, postStat) {
-		fmt.Fprintf(errWriter, "Error: --docmap %q changed between validation and open\n", *docmapFlag)
-		return 2
-	}
-	docmapData, err := io.ReadAll(io.LimitReader(f, maxDocmapBytes+1))
-	if err != nil {
-		fmt.Fprintf(errWriter, "Error: failed to read docmap %q: %v\n", *docmapFlag, err)
-		return 2
-	}
-	if int64(len(docmapData)) > maxDocmapBytes {
-		fmt.Fprintf(errWriter, "Error: --docmap %q exceeded %d-byte limit after open\n", *docmapFlag, maxDocmapBytes)
-		return 2
-	}
-	cfg, err := review.ParseDocMapConfigContent(string(docmapData), *docmapFlag)
+	// Parse docmap YAML.
+	cfg, err := review.ParseDocMapConfig(*docmapFlag)
 	if err != nil {
 		fmt.Fprintf(errWriter, "Error: failed to parse docmap %q: %v\n", *docmapFlag, err)
 		return 2

cmd/review-bot/validatedocmap_test.go

@@ -595,7 +595,7 @@ func TestValidateDocmapPath_DirSymlinkBypass(t *testing.T) {
 		t.Fatalf("EvalSymlinks(repoDir): %v", err)
 	}
 
-	if _, err := validateDocmapPath(attackPath, resolvedRoot); err == nil {
+	if err := validateDocmapPath(attackPath, resolvedRoot); err == nil {
 		t.Error("expected rejection of dir-symlink bypass, got nil error")
 	}
 }
@@ -649,48 +649,3 @@ mappings:
 		t.Errorf("expected exit 0 for './' prefixed covered file, got %d; stderr: %q", code, stderr)
 	}
 }
-
-// TestValidateDocmapPath_InRepoSymlinkAllowed verifies that an in-repo
-// file-level symlink whose resolved target is still within the repo root is
-// accepted. This is the positive case for the issue #150 behavioral change:
-// only symlinks that escape the root are rejected; intra-repo symlinks are
-// allowed because EvalSymlinks resolves the target and the confinement check
-// is applied to the resolved path, not the symlink entry itself.
-func TestValidateDocmapPath_InRepoSymlinkAllowed(t *testing.T) {
-	dir := t.TempDir()
-
-	// Create the real docmap file inside the repo root.
-	if err := os.MkdirAll(filepath.Join(dir, ".review-bot"), 0o755); err != nil {
-		t.Fatalf("MkdirAll: %v", err)
-	}
-	realDocmap := filepath.Join(dir, ".review-bot", "doc-map-real.yml")
-	if err := os.WriteFile(realDocmap, []byte("mappings: []\n"), 0o644); err != nil {
-		t.Fatalf("WriteFile: %v", err)
-	}
-
-	// Create a symlink inside the repo root that points to the real file
-	// (also inside the root).
-	symlinkPath := filepath.Join(dir, ".review-bot", "doc-map-link.yml")
-	if err := os.Symlink(realDocmap, symlinkPath); err != nil {
-		t.Skipf("cannot create symlink (platform may not support it): %v", err)
-	}
-
-	// Resolve dir to a symlink-free root, as runValidateDocmap does.
-	resolvedRoot, err := filepath.EvalSymlinks(dir)
-	if err != nil {
-		t.Fatalf("EvalSymlinks(dir): %v", err)
-	}
-
-	// In-repo symlink whose target is within root: must be accepted.
-	resolved, err := validateDocmapPath(symlinkPath, resolvedRoot)
-	if err != nil {
-		t.Fatalf("expected in-repo symlink to be accepted, got error: %v", err)
-	}
-	// The returned resolved path must be the real file (not the symlink entry).
-	// validateDocmapPath calls filepath.EvalSymlinks internally, so the returned
-	// path is always the fully-resolved real path — it can never equal the
-	// symlink entry itself.
-	if resolved == symlinkPath {
-		t.Errorf("expected resolved path to differ from symlink path")
-	}
-}