From 86383a18c20493e3738d77af17d15b4bc8db1c24 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Sun, 16 Oct 2022 16:57:54 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- prepare_datasets.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/prepare_datasets.py b/prepare_datasets.py index 2722445..cce6906 100644 --- a/prepare_datasets.py +++ b/prepare_datasets.py @@ -9,5 +9,24 @@ filenames = [os.path.join(base_path, f) for f in filenames] for fn in filenames: with tarfile.open(fn) as tar: - tar.extractall() + 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)