From 0ec10f52a39bc1c1d86e7801d0e921497fa6f165 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Sat, 19 Nov 2022 10:03:51 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- open_bot/utils.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/open_bot/utils.py b/open_bot/utils.py index 4fa8db0..4169f92 100644 --- a/open_bot/utils.py +++ b/open_bot/utils.py @@ -24,7 +24,26 @@ def download_pretrained_model(): tempdir = tempfile.mkdtemp() logger.info("extracting archive file {} to temp dir {}".format(resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) return tempdir