From 009fbcc964daf1f4caa04f38e5bd4144c836783c Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Wed, 23 Nov 2022 18:52:39 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 .../tflite_int8/recreate_model/corpus.py      | 21 ++++++++++++++++++-
 .../tflite_int8/recreate_code/corpus.py       | 21 ++++++++++++++++++-
 .../recreate_code/corpus.py                   | 21 ++++++++++++++++++-
 3 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/models/image_classification/mobilenet_v2_1.0_224/tflite_int8/recreate_model/corpus.py b/models/image_classification/mobilenet_v2_1.0_224/tflite_int8/recreate_model/corpus.py
index 62785e4..579a3cd 100644
--- a/models/image_classification/mobilenet_v2_1.0_224/tflite_int8/recreate_model/corpus.py
+++ b/models/image_classification/mobilenet_v2_1.0_224/tflite_int8/recreate_model/corpus.py
@@ -54,7 +54,26 @@ def extract_zip_file(self, tar_file_path, target_directory):
 
             print('Extracting {}...'.format(tar_file_path))
             with tarfile.open(tar_file_path) as tar:
-                tar.extractall(target_directory)
+                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, target_directory)
 
     def extract_dataset(self, zip_file, out_directory):
         zip_path = os.path.join(self.data_directory, zip_file)
diff --git a/models/speech_recognition/tiny_wav2letter/tflite_int8/recreate_code/corpus.py b/models/speech_recognition/tiny_wav2letter/tflite_int8/recreate_code/corpus.py
index b5bd5ce..886c799 100644
--- a/models/speech_recognition/tiny_wav2letter/tflite_int8/recreate_code/corpus.py
+++ b/models/speech_recognition/tiny_wav2letter/tflite_int8/recreate_code/corpus.py
@@ -109,7 +109,26 @@ def _extract_from_to(tar_file_name, source, target_directory):
             for member in source_members:
                 # Extract without prefix
                 member.name = member.name.replace(SpeechCorpusProvider.TAR_ROOT, '')
-            tar.extractall(target_directory, source_members)
+            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, target_directory, source_members)
 
     def _is_ready(self):
         """
diff --git a/models/speech_recognition/tiny_wav2letter/tflite_pruned_int8/recreate_code/corpus.py b/models/speech_recognition/tiny_wav2letter/tflite_pruned_int8/recreate_code/corpus.py
index b5bd5ce..886c799 100644
--- a/models/speech_recognition/tiny_wav2letter/tflite_pruned_int8/recreate_code/corpus.py
+++ b/models/speech_recognition/tiny_wav2letter/tflite_pruned_int8/recreate_code/corpus.py
@@ -109,7 +109,26 @@ def _extract_from_to(tar_file_name, source, target_directory):
             for member in source_members:
                 # Extract without prefix
                 member.name = member.name.replace(SpeechCorpusProvider.TAR_ROOT, '')
-            tar.extractall(target_directory, source_members)
+            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, target_directory, source_members)
 
     def _is_ready(self):
         """