From a3c24c0cd2e8e690b9ea40da73d3d146378e9bf9 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Mon, 10 Oct 2022 06:23:17 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- .../pytorch_pretrained/modeling.py | 21 ++++++++++++++++++- .../pytorch_pretrained_bert/modeling.py | 21 ++++++++++++++++++- 2 files changed, 40 insertions(+), 2 deletions(-) diff --git a/Bert_Variations/pytorch_pretrained/modeling.py b/Bert_Variations/pytorch_pretrained/modeling.py index b9b6837..5d4e7ec 100644 --- a/Bert_Variations/pytorch_pretrained/modeling.py +++ b/Bert_Variations/pytorch_pretrained/modeling.py @@ -587,7 +587,26 @@ def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs): logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/Pretrain_Bert/pytorch_pretrained_bert/modeling.py b/Pretrain_Bert/pytorch_pretrained_bert/modeling.py index 55c6d9d..f80518a 100644 --- a/Pretrain_Bert/pytorch_pretrained_bert/modeling.py +++ b/Pretrain_Bert/pytorch_pretrained_bert/modeling.py @@ -581,7 +581,26 @@ def from_pretrained(cls, pretrained_model_name_or_path, state_dict=None, cache_d logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME)