diff --git a/preprocessor/utils.py b/preprocessor/utils.py index c94dc5e..231f88f 100644 --- a/preprocessor/utils.py +++ b/preprocessor/utils.py @@ -38,7 +38,26 @@ def unpack_tar(source_path, destination_path): print('[INFO] Unpacking {} to {}'.format(file_name, destination_path)) with tarfile.open(source_path) as tar: root_name = tar.getnames()[0] - tar.extractall(destination_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, destination_path) print('[INFO] Cleaning {} directory'.format(destination_path)) #Move files destination path