diff --git a/net2net/data/utils.py b/net2net/data/utils.py index f36fe6d..e3d9d46 100644 --- a/net2net/data/utils.py +++ b/net2net/data/utils.py @@ -9,10 +9,48 @@ def unpack(path): if path.endswith("tar.gz"): with tarfile.open(path, "r:gz") as tar: - tar.extractall(path=os.path.split(path)[0]) + 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=os.path.split(path)["0"]) elif path.endswith("tar"): with tarfile.open(path, "r:") as tar: - tar.extractall(path=os.path.split(path)[0]) + 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=os.path.split(path)["0"]) elif path.endswith("zip"): with zipfile.ZipFile(path, "r") as f: f.extractall(path=os.path.split(path)[0])