Adding tarfile member sanitization to extractall() (#372)

examples/pytorch/bert/bert-quantization-sparsity/modeling.py

@@ -768,7 +768,26 @@ def from_pretrained(cls, pretrained_model_name_or_path, state_dict=None, cache_d
             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)

examples/pytorch/nemo.py

@@ -37,7 +37,29 @@ def unpack_nemo_ckpt(
     for tar_mode in ["r:", "r:gz"]:
         try:
             with tarfile.open(nemo_archive_path, mode=tar_mode) as tar_file:
-                tar_file.extractall(path=out_dir_path)
+
+                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_file, path=out_dir_path)
             return out_dir_path
         except tarfile.ReadError:
             pass