From 3ce6ec85c493fff074291e3bd3c774ce0d65a40f Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Sat, 15 Oct 2022 22:05:39 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 pipelines/tweets/old_scripts/evaluate.py      | 24 ++++++++++++++++++-
 pipelines/tweets/scripts_eval/evaluate.py     | 24 ++++++++++++++++++-
 .../xgboost_source_dir/_repack_model.py       | 21 +++++++++++++++-
 3 files changed, 66 insertions(+), 3 deletions(-)

diff --git a/pipelines/tweets/old_scripts/evaluate.py b/pipelines/tweets/old_scripts/evaluate.py
index 6ddf06d..bb19e8e 100644
--- a/pipelines/tweets/old_scripts/evaluate.py
+++ b/pipelines/tweets/old_scripts/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"))
diff --git a/pipelines/tweets/scripts_eval/evaluate.py b/pipelines/tweets/scripts_eval/evaluate.py
index 697c75e..961d1ab 100644
--- a/pipelines/tweets/scripts_eval/evaluate.py
+++ b/pipelines/tweets/scripts_eval/evaluate.py
@@ -26,7 +26,29 @@
     logger.info(f"Evaluation:xgboost:version={xgb.__version__}:")
     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=".")
 
     model = None
 
diff --git a/pipelines/tweets/xgboost_source_dir/_repack_model.py b/pipelines/tweets/xgboost_source_dir/_repack_model.py
index f98f170..0eb9063 100644
--- a/pipelines/tweets/xgboost_source_dir/_repack_model.py
+++ b/pipelines/tweets/xgboost_source_dir/_repack_model.py
@@ -60,7 +60,26 @@ def repack(inference_script, model_archive, dependencies=None, source_dir=None):
         # extract the contents of the previous training job's model archive to the "src"
         # directory of this training job
         with tarfile.open(name=local_path, mode="r:gz") as tf:
-            tf.extractall(path=src_dir)
+            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=src_dir)
 
         if source_dir:
             # copy /opt/ml/code to code/