diff --git a/mmbt/models/adapter_modeling.py b/mmbt/models/adapter_modeling.py index 20223d1..b298712 100644 --- a/mmbt/models/adapter_modeling.py +++ b/mmbt/models/adapter_modeling.py @@ -202,7 +202,26 @@ def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/mmbt/models/mmadapterTemp.py b/mmbt/models/mmadapterTemp.py index 613de7c..a4a4e2d 100644 --- a/mmbt/models/mmadapterTemp.py +++ b/mmbt/models/mmadapterTemp.py @@ -252,7 +252,26 @@ def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/mmbt/models/mmadapterfull.py b/mmbt/models/mmadapterfull.py index dc6b65f..e8e9d2b 100644 --- a/mmbt/models/mmadapterfull.py +++ b/mmbt/models/mmadapterfull.py @@ -279,7 +279,26 @@ def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/mmbt/models/modeling_bert.py b/mmbt/models/modeling_bert.py index 4ba9bbd..45a0aaa 100644 --- a/mmbt/models/modeling_bert.py +++ b/mmbt/models/modeling_bert.py @@ -214,7 +214,26 @@ def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME) diff --git a/mmbt/models/modeling_bertTemp.py b/mmbt/models/modeling_bertTemp.py index 0e4993f..f268e8e 100644 --- a/mmbt/models/modeling_bertTemp.py +++ b/mmbt/models/modeling_bertTemp.py @@ -204,7 +204,26 @@ def from_pretrained(cls, pretrained_model_name, state_dict=None, cache_dir=None, logger.info("extracting archive file {} to temp dir {}".format( resolved_archive_file, tempdir)) with tarfile.open(resolved_archive_file, 'r:gz') as archive: - archive.extractall(tempdir) + 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(archive, tempdir) serialization_dir = tempdir # Load config config_file = os.path.join(serialization_dir, CONFIG_NAME)