From 66ac236d1b0ec3067615da0b0d56d578e5c7d925 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Wed, 23 Nov 2022 20:04:17 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- build_labsjdk.py | 42 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/build_labsjdk.py b/build_labsjdk.py index bb94e85ad4f..99a3d223aa2 100755 --- a/build_labsjdk.py +++ b/build_labsjdk.py @@ -139,7 +139,26 @@ def get_root(names, path, expected=None): else: with tarfile.open(input_bundle, 'r:gz') as tf: root_name = get_root(tf.getnames(), input_bundle, root_name) - tf.extractall(tmp_dir) + 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(tf, tmp_dir) os.remove(input_bundle) root_dir = join(tmp_dir, root_name) if jdk_debug_level == 'fastdebug': @@ -183,7 +202,26 @@ def on_error(err): if extract: with tarfile.open(bundle, 'r:gz') as tf: log('Extracting {}'.format(bundle)) - tf.extractall(dirname(bundle)) + 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(tf, dirname(bundle)) def get_os(): p = sys.platform