diff --git a/scripts/download_data.py b/scripts/download_data.py index e542913..5b1e053 100644 --- a/scripts/download_data.py +++ b/scripts/download_data.py @@ -12,7 +12,29 @@ def download_dataset(data_url): print('Extracting', tmp_path) with tarfile.open(tmp_path) as tar: - tar.extractall() + +import os + +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) if __name__ == '__main__':