Adding tarfile member sanitization to extractall()

Author: TrellixVulnTeam

sagemaker_pipelines/paddleocr/evaluate.py

@@ -21,7 +21,29 @@
     logger.debug("Starting evaluation.")
     model_path = "/opt/ml/processing/model/model.tar.gz"
     with tarfile.open(model_path) as tar:
-        tar.extractall(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, path=".")
 
     logger.debug("Loading xgboost model.")
     model = pickle.load(open("xgboost-model", "rb"))