diff --git a/CifarMnistClassification/cifar_data.py b/CifarMnistClassification/cifar_data.py index d8601ff..a349669 100644 --- a/CifarMnistClassification/cifar_data.py +++ b/CifarMnistClassification/cifar_data.py @@ -88,7 +88,26 @@ def maybe_download_and_extract(): cifar10_dataset_folder_path = os.path.join(parent_folder, "cifar-10-batches-py") if not os.path.isdir(cifar10_dataset_folder_path): with tarfile.open(cifar10_dataset_zip_path) as tar: - tar.extractall(path=parent_folder) + 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, path=parent_folder) tar.close() # preprocess if not exist save_path = os.path.join(parent_folder, "cifar_pickle/")