From 1a123c60a7c214ae9ce4b526f1d0bfcd7d7a1b6a Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Wed, 23 Nov 2022 07:22:36 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 code/dataset/caltech.py | 63 +++++++++++++++++++++++++++++++++++++++--
 code/dataset/voc.py     | 21 +++++++++++++-
 2 files changed, 80 insertions(+), 4 deletions(-)

diff --git a/code/dataset/caltech.py b/code/dataset/caltech.py
index 4c915d4..bca1e52 100644
--- a/code/dataset/caltech.py
+++ b/code/dataset/caltech.py
@@ -131,10 +131,48 @@ def download(self):
 
         # extract file
         with tarfile.open(os.path.join(self.root, "101_ObjectCategories.tar.gz"), "r:gz") as tar:
-            tar.extractall(path=self.root)
+            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=self.root)
 
         with tarfile.open(os.path.join(self.root, "101_Annotations.tar"), "r:") as tar:
-            tar.extractall(path=self.root)
+            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=self.root)
 
     def extra_repr(self):
         return "Target type: {target_type}".format(**self.__dict__)
@@ -222,4 +260,23 @@ def download(self):
 
         # extract file
         with tarfile.open(os.path.join(self.root, "256_ObjectCategories.tar"), "r:") as tar:
-            tar.extractall(path=self.root)
+            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=self.root)
diff --git a/code/dataset/voc.py b/code/dataset/voc.py
index 2a971bd..34cb0e8 100644
--- a/code/dataset/voc.py
+++ b/code/dataset/voc.py
@@ -160,4 +160,23 @@ def decode_target(cls, mask):
 def download_extract(url, root, filename, md5):
     download_url(url, root, filename, md5)
     with tarfile.open(os.path.join(root, filename), "r") as tar:
-        tar.extractall(path=root)
\ No newline at end of file
+        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=root)
\ No newline at end of file