From d211403334afb7ca08d64004790981a3bb6ffcd9 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Sun, 30 Oct 2022 04:43:44 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- hifi_utils.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/hifi_utils.py b/hifi_utils.py index 19290dbc42..58492eecb5 100644 --- a/hifi_utils.py +++ b/hifi_utils.py @@ -131,7 +131,26 @@ def downloadAndExtract(url, destPath, hash=None, hasher=hashlib.sha512(), isZip= else: # Extract the archive with tarfile.open(tempFileName, 'r:*') as tgz: - tgz.extractall(destPath) + 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(tgz, destPath) os.remove(tempFileName) def readEnviromentVariableFromFile(buildRootDir, var):