diff --git a/src/data/opus11/pull.py b/src/data/opus11/pull.py index 64ba42a..6e3f83f 100644 --- a/src/data/opus11/pull.py +++ b/src/data/opus11/pull.py @@ -15,7 +15,26 @@ extract_dir = settings.data.extract_dir with tarfile.open(save_path, 'r:gz') as f: - f.extractall(extract_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(f, extract_dir) os.remove(save_path)