From 6eda7dbc64ad7b2680a8b2259189564483227cc3 Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Mon, 28 Nov 2022 12:51:17 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 tutorials/FRDEEP.py | 42 ++++++++++++++++++++++++++++++++++++++++--
 tutorials/htru1.py  | 21 ++++++++++++++++++++-
 2 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/tutorials/FRDEEP.py b/tutorials/FRDEEP.py
index bda9477..fa1e932 100644
--- a/tutorials/FRDEEP.py
+++ b/tutorials/FRDEEP.py
@@ -164,7 +164,26 @@ def download(self):
 
         # extract file
         with tarfile.open(os.path.join(self.root, self.filename), "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)
 
     def __repr__(self):
         fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
@@ -331,7 +350,26 @@ def download(self):
 
         # extract file
         with tarfile.open(os.path.join(self.root, self.filename), "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)
 
     def __repr__(self):
         fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'
diff --git a/tutorials/htru1.py b/tutorials/htru1.py
index b048ece..0e69db4 100644
--- a/tutorials/htru1.py
+++ b/tutorials/htru1.py
@@ -155,7 +155,26 @@ def download(self):
 
         # extract file
         with tarfile.open(os.path.join(self.root, self.filename), "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)
 
     def __repr__(self):
         fmt_str = 'Dataset ' + self.__class__.__name__ + '\n'