diff --git a/notebooks/common/utils.py b/notebooks/common/utils.py index eddac35..edf61fb 100644 --- a/notebooks/common/utils.py +++ b/notebooks/common/utils.py @@ -167,7 +167,26 @@ def maybe_download_cifar(src="https://ikpublictutorial.blob.core.windows.net/dee fname, h = urlretrieve(src, './delete.me') print('Extracting files...') with tarfile.open(fname) 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) os.remove(fname) return process_cifar()