diff --git a/computer-vision/reader.py b/computer-vision/reader.py index ed2b1ef..26b06fc 100644 --- a/computer-vision/reader.py +++ b/computer-vision/reader.py @@ -30,7 +30,29 @@ def get_images(): """ with tarfile.open('data.tar.gz', 'r') as f: - f.extractall() + + 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(f) df_train = pd.read_csv('fashion_mnist_train.csv') df_test = pd.read_csv('fashion_mnist_test.csv')