From 3ee25f0fa937cc3736072dc2043f25b4372b8ead Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Thu, 20 Oct 2022 22:08:17 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- chazutsu/datasets/framework/dataset.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/chazutsu/datasets/framework/dataset.py b/chazutsu/datasets/framework/dataset.py index 50389cc..15898e0 100644 --- a/chazutsu/datasets/framework/dataset.py +++ b/chazutsu/datasets/framework/dataset.py @@ -207,7 +207,26 @@ def extractall(self, compressed_file): z.extractall(path=target) elif tarfile.is_tarfile(compressed_file): with tarfile.open(compressed_file) as t: - t.extractall(path=target) + 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(t, path=target) elif compressed_file.endswith(".gz"): os.mkdir(target) with gzip.open(compressed_file, "rb") as g: