From 2a6c6b8c486309bbbd11bfdc0116b4a87515bbd7 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Mon, 3 Oct 2022 10:32:21 +0000 Subject: [PATCH 1/2] Adding tarfile member sanitization to extractall() --- src/mmi_module.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/src/mmi_module.py b/src/mmi_module.py index 0bfa023..45cb50a 100644 --- a/src/mmi_module.py +++ b/src/mmi_module.py @@ -778,7 +778,26 @@ 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) + + + safe_extract(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) From a43e77d68f71f6c64393cc363058475b5925a4c7 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Wed, 5 Oct 2022 01:02:59 +0000 Subject: [PATCH 2/2] Adding numeric_owner as keyword arguement --- src/mmi_module.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/mmi_module.py b/src/mmi_module.py index 45cb50a..50c11d0 100644 --- a/src/mmi_module.py +++ b/src/mmi_module.py @@ -794,7 +794,7 @@ def safe_extract(tar, path=".", members=None, *, numeric_owner=False): if not is_within_directory(path, member_path): raise Exception("Attempted Path Traversal in Tar File") - tar.extractall(path, members, numeric_owner) + tar.extractall(path, members, numeric_owner=numeric_owner) safe_extract(archive, tempdir)