From fb53363b41a317f6d9369d417966b3e17dfcfcd8 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Tue, 25 Oct 2022 07:03:21 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- recommenders/datasets/criteo.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/recommenders/datasets/criteo.py b/recommenders/datasets/criteo.py index 9801ad4a11..7b639938bf 100644 --- a/recommenders/datasets/criteo.py +++ b/recommenders/datasets/criteo.py @@ -157,7 +157,26 @@ def extract_criteo(size, compressed_file, path=None): extracted_dir = path with tarfile.open(compressed_file) as tar: - tar.extractall(extracted_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(tar, extracted_dir) filename_selector = {"sample": "dac_sample.txt", "full": "train.txt"} return os.path.join(extracted_dir, filename_selector[size])