From 0f4d0c6fd093959aa3d2f284524f08dd031a5e65 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Fri, 25 Nov 2022 23:43:29 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- generator_data/scripts/stog/utils/archival.py | 21 ++++++++++++++++++- generator_data/stog/utils/archival.py | 21 ++++++++++++++++++- 2 files changed, 40 insertions(+), 2 deletions(-) diff --git a/generator_data/scripts/stog/utils/archival.py b/generator_data/scripts/stog/utils/archival.py index 568aab8..6aa9f3e 100644 --- a/generator_data/scripts/stog/utils/archival.py +++ b/generator_data/scripts/stog/utils/archival.py @@ -92,7 +92,26 @@ def load_archive(archive_file: str, tempdir = tempfile.mkdtemp() logger.info(f"extracting archive file {resolved_archive_file} to temp dir {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 diff --git a/generator_data/stog/utils/archival.py b/generator_data/stog/utils/archival.py index 568aab8..6aa9f3e 100644 --- a/generator_data/stog/utils/archival.py +++ b/generator_data/stog/utils/archival.py @@ -92,7 +92,26 @@ def load_archive(archive_file: str, tempdir = tempfile.mkdtemp() logger.info(f"extracting archive file {resolved_archive_file} to temp dir {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