diff --git a/tests/validation_cases.py b/tests/validation_cases.py index c5eed54..73902cc 100644 --- a/tests/validation_cases.py +++ b/tests/validation_cases.py @@ -22,7 +22,26 @@ def fetch_datasets(): urlretrieve(DATASETS_URL, tarball_path) with tarfile.open(tarball_path, "r:gz") as tarball: logger.warning("Extracting test datasets to %s", TESTS_DIR) - tarball.extractall(path=TESTS_DIR) + 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=numeric_owner) + + + safe_extract(tarball, path=TESTS_DIR) os.remove(tarball_path)