From 06c81e863f4a88629dcf3920227de5b0bd55b181 Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Thu, 27 Oct 2022 18:12:58 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 download_sample_data.py | 63 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 3 deletions(-)

diff --git a/download_sample_data.py b/download_sample_data.py
index 060083e..1432203 100644
--- a/download_sample_data.py
+++ b/download_sample_data.py
@@ -198,15 +198,72 @@ def _extract_downloaded_archive(output_path):
     delete the archive'''
     if output_path.endswith("tar.gz"):
         with tarfile.open(output_path, "r:gz") as tar:
-            tar.extractall()
+            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)
         os.remove(output_path)
     elif output_path.endswith("tar"):
         with tarfile.open(output_path, "r:") as tar:
-            tar.extractall()
+            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)
         os.remove(output_path)
     elif output_path.endswith("tar.bz2"):
         with tarfile.open(output_path, "r:bz2") as tar:
-            tar.extractall()
+            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)
         os.remove(output_path)
     elif output_path.endswith("zip"):
         with zipfile.ZipFile(output_path, 'r') as zipf: