diff --git a/iirc/utils/download_cifar.py b/iirc/utils/download_cifar.py index 7bc1ccc..d9deb95 100644 --- a/iirc/utils/download_cifar.py +++ b/iirc/utils/download_cifar.py @@ -33,7 +33,26 @@ def download_extract_cifar100(root="data"): logging.info("extracting dataset") if tar_file_path is not None: with tarfile.open(tar_file_path, 'r') as tar: - tar.extractall(root) + 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, root) print("dataset extracted") logging.info("dataset extracted")