From 94f14e89f1e39856a1df87e50caff19f4278a6d3 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Sat, 10 Dec 2022 08:16:19 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- mlprimitives/datasets.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/mlprimitives/datasets.py b/mlprimitives/datasets.py index e8ebc589..0831a9a5 100644 --- a/mlprimitives/datasets.py +++ b/mlprimitives/datasets.py @@ -212,7 +212,26 @@ def _download(dataset_name, dataset_path): LOGGER.debug('Extracting dataset into %s', DATA_PATH) with tarfile.open(fileobj=bytes_io, mode='r:gz') as tf: - tf.extractall(DATA_PATH) + 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, DATA_PATH) def _load(dataset_name):