diff --git a/scripts/createdataset.py b/scripts/createdataset.py index 122a764..c966182 100644 --- a/scripts/createdataset.py +++ b/scripts/createdataset.py @@ -340,7 +340,29 @@ def main(): # untar input for tf_name in sorted((args.outdir / args.sub_dir).glob("train-00*.tar")): with tarfile.open(tf_name) as tf: - tf.extractall(tmpdir) + + 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(tf, tmpdir) print("Write balanced shards from deadtree samples") df = pd.read_csv(args.outdir / args.stats_file)