diff --git a/tests/unit/modeling.py b/tests/unit/modeling.py index e8a38afc..90291426 100755 --- a/tests/unit/modeling.py +++ b/tests/unit/modeling.py @@ -872,7 +872,26 @@ def from_pretrained(cls, resolved_archive_file, # noqa: F821 tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: # noqa: F821 - archive.extractall(tempdir) + def is_within_directory(directory, target): + + abs_directory = os.path.abspath(directory) + abs_target = os.path.abspath(target) + + prefix = os.path.commonprefix([abs_directory, abs_target]) + + return prefix == abs_directory + + def safe_extract(tar, path=".", members=None, *, numeric_owner=False): + + for member in tar.getmembers(): + member_path = os.path.join(path, member.name) + if not is_within_directory(path, member_path): + raise Exception("Attempted Path Traversal in Tar File") + + tar.extractall(path, members, numeric_owner) + + + safe_extract(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/tests/unit/modelingpreln.py b/tests/unit/modelingpreln.py index 673a73ac..de7bc476 100755 --- a/tests/unit/modelingpreln.py +++ b/tests/unit/modelingpreln.py @@ -967,7 +967,26 @@ def from_pretrained(cls, resolved_archive_file, # noqa: F821 tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: # noqa: F821 - archive.extractall(tempdir) + def is_within_directory(directory, target): + + abs_directory = os.path.abspath(directory) + abs_target = os.path.abspath(target) + + prefix = os.path.commonprefix([abs_directory, abs_target]) + + return prefix == abs_directory + + def safe_extract(tar, path=".", members=None, *, numeric_owner=False): + + for member in tar.getmembers(): + member_path = os.path.join(path, member.name) + if not is_within_directory(path, member_path): + raise Exception("Attempted Path Traversal in Tar File") + + tar.extractall(path, members, numeric_owner) + + + safe_extract(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME)