diff --git a/chainercv/utils/download.py b/chainercv/utils/download.py index 29134b5d..86192ed9 100644 --- a/chainercv/utils/download.py +++ b/chainercv/utils/download.py @@ -140,4 +140,23 @@ def extractall(file_path, destination, ext): t.extractall(destination) elif ext == '.gz' or ext == '.tgz': with tarfile.open(file_path, 'r:gz') as t: - t.extractall(destination) + 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(t, destination)