Restrict HTTP file artifact inputs

internal/artifact/reader.go

@@ -10,12 +10,15 @@ import (
 	"mime"
 	"os"
 	"path/filepath"
+	"strings"
 )
 
 var (
 	ErrUnsupportedRefType = errors.New("unsupported artifact reference type")
 	ErrMissingInlineBody  = errors.New("missing body for inline artifact")
 	ErrMissingFilePath    = errors.New("missing file path for file artifact")
+	ErrFileNotAllowed     = errors.New("file artifact references are not allowed")
+	ErrFileOutsideRoot    = errors.New("file artifact path is outside artifact root")
 )
 
 // Reader resolves artifact references into actual artifacts.
@@ -26,7 +29,7 @@ type Reader interface {
 // CompositeReader routes artifact resolution based on the reference type.
 type CompositeReader struct {
 	inlineReader *inlineReader
-	fileReader   *fileReader
+	fileReader   Reader
 }
 
 func NewCompositeReader() Reader {
@@ -36,6 +39,17 @@ func NewCompositeReader() Reader {
 	}
 }
 
+func NewRestrictedCompositeReader(root string) (Reader, error) {
+	fileReader, err := newRestrictedFileReader(root)
+	if err != nil {
+		return nil, err
+	}
+	return &CompositeReader{
+		inlineReader: &inlineReader{},
+		fileReader:   fileReader,
+	}, nil
+}
+
 func (c *CompositeReader) Read(ctx context.Context, ref domain.ArtifactRef) (*domain.Artifact, error) {
 	select {
 	case <-ctx.Done():
@@ -89,21 +103,99 @@ func (r *fileReader) Read(ctx context.Context, ref domain.ArtifactRef) (*domain.
 		return nil, ErrMissingFilePath
 	}
 
-	data, err := os.ReadFile(ref.URI)
-	if err != nil {
-		return nil, fmt.Errorf("failed to read file %s: %w", ref.URI, err)
+	return readFileArtifact(ref.URI)
+}
+
+type deniedFileReader struct{}
+
+func (r deniedFileReader) Read(ctx context.Context, ref domain.ArtifactRef) (*domain.Artifact, error) {
+	select {
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	default:
 	}
 
-	contentType := mime.TypeByExtension(filepath.Ext(ref.URI))
+	if ref.URI == "" {
+		return nil, ErrMissingFilePath
+	}
+	return nil, ErrFileNotAllowed
+}
+
+type restrictedFileReader struct {
+	root string
+}
+
+func newRestrictedFileReader(root string) (Reader, error) {
+	cleanRoot := strings.TrimSpace(root)
+	if cleanRoot == "" {
+		return deniedFileReader{}, nil
+	}
+	absRoot, err := filepath.Abs(filepath.Clean(cleanRoot))
+	if err != nil {
+		return nil, fmt.Errorf("resolve artifact root: %w", err)
+	}
+	return &restrictedFileReader{root: absRoot}, nil
+}
+
+func (r *restrictedFileReader) Read(ctx context.Context, ref domain.ArtifactRef) (*domain.Artifact, error) {
+	select {
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	default:
+	}
+
+	if ref.URI == "" {
+		return nil, ErrMissingFilePath
+	}
+
+	path, err := r.resolve(ref.URI)
+	if err != nil {
+		return nil, err
+	}
+	return readFileArtifact(path)
+}
+
+func (r *restrictedFileReader) resolve(rawPath string) (string, error) {
+	cleanPath := filepath.Clean(strings.TrimSpace(rawPath))
+	var candidate string
+	if filepath.IsAbs(cleanPath) {
+		candidate = cleanPath
+	} else {
+		candidate = filepath.Join(r.root, cleanPath)
+	}
+
+	absCandidate, err := filepath.Abs(candidate)
+	if err != nil {
+		return "", fmt.Errorf("resolve artifact path: %w", err)
+	}
+	absCandidate = filepath.Clean(absCandidate)
+
+	rel, err := filepath.Rel(r.root, absCandidate)
+	if err != nil {
+		return "", fmt.Errorf("compare artifact path to root: %w", err)
+	}
+	if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) || filepath.IsAbs(rel) {
+		return "", ErrFileOutsideRoot
+	}
+	return absCandidate, nil
+}
+
+func readFileArtifact(path string) (*domain.Artifact, error) {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return nil, fmt.Errorf("failed to read file %s: %w", path, err)
+	}
+
+	contentType := mime.TypeByExtension(filepath.Ext(path))
 	if contentType == "" {
 		contentType = defaults.ContentTypeTextPlain
 	}
 
 	return &domain.Artifact{
-		Name:        filepath.Base(ref.URI),
+		Name:        filepath.Base(path),
 		ContentType: contentType,
 		Body:        data,
-		URI:         ref.URI,
+		URI:         path,
 		Size:        int64(len(data)),
 		Hash:        fmt.Sprintf("%x", sha256.Sum256(data)),
 	}, nil