diff --git a/Source Code Files/ml/src/adfa_preprocessing.py b/Source Code Files/ml/src/adfa_preprocessing.py index 57886f3..af71055 100644 --- a/Source Code Files/ml/src/adfa_preprocessing.py +++ b/Source Code Files/ml/src/adfa_preprocessing.py @@ -89,7 +89,29 @@ def unpack_data(): if not Path("../data/PLAID").exists(): with tarfile.open("../data/PLAID.tar.xz") as f: - f.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(f, ".") if __name__ == "__main__":