From 200649a2cf17d5d7ab7dd76803e15c7ea76b26c2 Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Thu, 27 Oct 2022 20:42:53 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- ssd/src/utils/common/archives.py | 63 ++++++++++++++++++++++++++++++-- ssd/utils/common/archives.py | 63 ++++++++++++++++++++++++++++++-- 2 files changed, 120 insertions(+), 6 deletions(-) diff --git a/ssd/src/utils/common/archives.py b/ssd/src/utils/common/archives.py index c5b5b31..5ffec9a 100644 --- a/ssd/src/utils/common/archives.py +++ b/ssd/src/utils/common/archives.py @@ -43,15 +43,72 @@ def extract_archive(archive_path, destination_path): elif archive_filename.endswith(".tar"): archive_name = archive_filename[:-4] with tarfile.open(archive_path, "r:") as file: - file.extractall(temp_path) +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_path) elif archive_filename.endswith(".tar.bz2"): archive_name = archive_filename[:-8] with tarfile.open(archive_path, "r:bz2") as file: - file.extractall(temp_path) +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_path) elif archive_filename.endswith(".tar.gz"): archive_name = archive_filename[:-7] with tarfile.open(archive_path, "r:gz") as file: - file.extractall(temp_path) +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_path) else: raise NotImplementedError("The type of the archive '{}' is currently not supported.".format(archive_filename)) diff --git a/ssd/utils/common/archives.py b/ssd/utils/common/archives.py index c5b5b31..5ffec9a 100644 --- a/ssd/utils/common/archives.py +++ b/ssd/utils/common/archives.py @@ -43,15 +43,72 @@ def extract_archive(archive_path, destination_path): elif archive_filename.endswith(".tar"): archive_name = archive_filename[:-4] with tarfile.open(archive_path, "r:") as file: - file.extractall(temp_path) +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_path) elif archive_filename.endswith(".tar.bz2"): archive_name = archive_filename[:-8] with tarfile.open(archive_path, "r:bz2") as file: - file.extractall(temp_path) +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_path) elif archive_filename.endswith(".tar.gz"): archive_name = archive_filename[:-7] with tarfile.open(archive_path, "r:gz") as file: - file.extractall(temp_path) +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_path) else: raise NotImplementedError("The type of the archive '{}' is currently not supported.".format(archive_filename))