diff --git a/compare_toi.py b/compare_toi.py index 1322072..32f17c6 100644 --- a/compare_toi.py +++ b/compare_toi.py @@ -42,7 +42,29 @@ def main(): tois = numpy.genfromtxt(tois_csv, delimiter=",", dtype=str).reshape(-1, 2) with tarfile.open(tar_file, "r") as tar: - tar.extractall(working_dir) + + import os + + 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(tar, working_dir) names = tar.getnames() for name in tqdm(names): diff --git a/save_roots.py b/save_roots.py index 01dba56..e9f7472 100644 --- a/save_roots.py +++ b/save_roots.py @@ -83,7 +83,29 @@ def main(): if len(tar.getnames()) == sum(collides): print(f"complete results exist: {tar_output}") continue - tar.extractall(working_dir) + + import os + + 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(tar, working_dir) if session is None: session = init_session(args)