Adding tarfile member sanitization to extractall()

ppdet/utils/download.py

@@ -422,7 +422,26 @@ def _decompress(fname):
 
     if fname.find('tar') >= 0:
         with tarfile.open(fname) as tf:
-            tf.extractall(path=fpath_tmp)
+            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(tf, path=fpath_tmp)
     elif fname.find('zip') >= 0:
         with zipfile.ZipFile(fname) as zf:
             zf.extractall(path=fpath_tmp)