From d932b7f3ce90ba6b8fa592f4e563053dd7432e7c Mon Sep 17 00:00:00 2001 From: TrellixVulnTeam Date: Thu, 20 Oct 2022 05:42:33 +0000 Subject: [PATCH] Adding tarfile member sanitization to extractall() --- .../scripts/dataset/prepare_imagenet.py | 42 ++++++++++++++++++- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/final-project/model_zoo/pytorch_resnest/scripts/dataset/prepare_imagenet.py b/final-project/model_zoo/pytorch_resnest/scripts/dataset/prepare_imagenet.py index eb9efe7..4859862 100644 --- a/final-project/model_zoo/pytorch_resnest/scripts/dataset/prepare_imagenet.py +++ b/final-project/model_zoo/pytorch_resnest/scripts/dataset/prepare_imagenet.py @@ -51,7 +51,26 @@ def extract_train(tar_fname, target_dir, with_rec=False, num_thread=1): class_dir = os.path.splitext(class_fname)[0] os.mkdir(class_dir) with tarfile.open(class_fname) as f: - f.extractall(class_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(f, class_dir) os.remove(class_fname) pbar.update(1) pbar.close() @@ -60,7 +79,26 @@ def extract_val(tar_fname, target_dir, with_rec=False, num_thread=1): mkdir(target_dir) print('Extracting ' + tar_fname) with tarfile.open(tar_fname) as tar: - tar.extractall(target_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(tar, target_dir) # build rec file before images are moved into subfolders # move images to proper subfolders subprocess.call(["wget -qO- https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh | bash"],