From d17903d4e9f404593ffc1bdb7b4e710baae54662 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam <112716341+TrellixVulnTeam@users.noreply.github.com> Date: Thu, 27 Oct 2022 06:56:05 -0500 Subject: [PATCH] Adding tarfile member sanitization to extractall() (#803) --- clearml/storage/manager.py | 42 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/clearml/storage/manager.py b/clearml/storage/manager.py index 029c5c70..5e7b0828 100644 --- a/clearml/storage/manager.py +++ b/clearml/storage/manager.py @@ -165,10 +165,48 @@ class StorageManager(object): ZipFile(cached_file.as_posix()).extractall(path=temp_target_folder.as_posix()) elif suffix == ".tar.gz": with tarfile.open(cached_file.as_posix()) as file: - file.extractall(temp_target_folder.as_posix()) + 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(file, temp_target_folder.as_posix()) elif suffix == ".tgz": with tarfile.open(cached_file.as_posix(), mode='r:gz') as file: - file.extractall(temp_target_folder.as_posix()) + 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(file, temp_target_folder.as_posix()) if temp_target_folder != target_folder: # we assume we will have such folder if we already extract the file