Adding tarfile member sanitization to extractall()

data/vocab.py

@@ -228,7 +228,26 @@ def cache(self, name, cache, url=None):
                         zf.extractall(cache)
                 elif ext == 'gz':
                     with tarfile.open(dest, 'r:gz') as tar:
-                        tar.extractall(path=cache)
+                        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, path=cache)
             if not os.path.isfile(path):
                 raise RuntimeError('no vectors found at {}'.format(path))