From 9c598d9065fef2140eab38d0b554775435f00fc6 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Thu, 15 Dec 2022 17:32:54 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- .../pipelines/hello_world/load_data.py | 21 ++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/jupyterlab-and-elyra/pipelines/hello_world/load_data.py b/jupyterlab-and-elyra/pipelines/hello_world/load_data.py index c6c50b2..5fc6b9d 100644 --- a/jupyterlab-and-elyra/pipelines/hello_world/load_data.py +++ b/jupyterlab-and-elyra/pipelines/hello_world/load_data.py @@ -45,7 +45,26 @@ def download_from_public_url(url): print('Extracting downloaded file in directory "{}" ...' .format(data_dir)) with tarfile.open(downloaded_data_file, 'r') as tar: - tar.extractall(data_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, data_dir) print('Removing downloaded file ...') downloaded_data_file.unlink()