diff --git a/mmsim/download.py b/mmsim/download.py index e0f67b8..65fd5c8 100644 --- a/mmsim/download.py +++ b/mmsim/download.py @@ -76,5 +76,24 @@ def download_micromouseonline_mazes(download_path: Path): reveal_tar, headers = urlretrieve(url) with tarfile.open(reveal_tar) as tar: members = clean_tar_members(tar.getmembers()) - tar.extractall(str(download_path), members) + 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, str(download_path), members) os.remove(reveal_tar)