diff --git a/geotorch/utility/_download_utils.py b/geotorch/utility/_download_utils.py index b3afbec..7d55460 100644 --- a/geotorch/utility/_download_utils.py +++ b/geotorch/utility/_download_utils.py @@ -32,12 +32,50 @@ def _extract_archive(from_path, to_path) -> None: if _is_tar(from_path): print("Archive extraction started...") with tarfile.open(from_path, 'r') as tar: - tar.extractall(path=to_path) +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(tar, path=to_path) print("Archive extraction finished") elif _is_targz(from_path): print("Archive extraction started...") with tarfile.open(from_path, 'r:gz') as tar: - tar.extractall(path=to_path) +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(tar, path=to_path) print("Archive extraction finished") elif _is_gzip(from_path): print("Archive extraction started...")