diff --git a/wikimap/Utils/Utils.py b/wikimap/Utils/Utils.py index 17c151f..22a812f 100644 --- a/wikimap/Utils/Utils.py +++ b/wikimap/Utils/Utils.py @@ -15,7 +15,29 @@ def download_and_extract(url, output_path): urllib.urlretrieve(url, temp.name, reporthook=LogUtils.ProgressBar(url).report) logger.info('Extracting to {}...'.format(output_path)) with tarfile.open(temp.name) as tar: - tar.extractall(output_path) + + import os + + 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, output_path) class Bunch(object): def __init__(self, **kwds):