Adding tarfile member sanitization to extractall() (#424)

Co-authored-by: TrellixVulnTeam <kasimir.schulz@trellix.com>

fastNLP/io/file_utils.py

@@ -471,7 +471,26 @@ def untar_gz_file(file: Path, to: Path):
     import tarfile
 
     with tarfile.open(file, 'r:gz') as tar:
-        tar.extractall(to)
+        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, to)
 
 
 def ungzip_file(file: str, to: str, filename: str):