diff --git a/adnc/data/tasks/babi.py b/adnc/data/tasks/babi.py index 0eadbaa..8997e58 100755 --- a/adnc/data/tasks/babi.py +++ b/adnc/data/tasks/babi.py @@ -90,7 +90,29 @@ def download_data(data_dir): with urlopen(req) as files: with tarfile.open(fileobj=files, mode="r|gz") as tar: - tar.extractall(path=DEFAULT_DATA_FOLDER) + + 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, path=DEFAULT_DATA_FOLDER) data_dir = data_dir / folder_name diff --git a/adnc/data/tasks/cnn_rc.py b/adnc/data/tasks/cnn_rc.py index e499e1e..e2f9c8c 100644 --- a/adnc/data/tasks/cnn_rc.py +++ b/adnc/data/tasks/cnn_rc.py @@ -125,7 +125,26 @@ def download_data(data_dir): print("### Extract CNN data") with urlopen(req) as files: with tarfile.open(fileobj=files, mode="r|gz") as tar: - tar.extractall(path=DEFAULT_DATA_FOLDER) + 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, path=DEFAULT_DATA_FOLDER) print("### CNN data complete") data_dir = data_dir / folder_name