Adding tarfile member sanitization to extractall() (#223)

Author: TrellixVulnTeam

genomepy/files.py

@@ -188,7 +188,26 @@ def extract_tarball(fname, outfile=None, concat=True) -> Union[str, None]:
     # Extract files to temporary directory
     tmp_dir = mkdtemp(dir=os.path.dirname(outfile))
     with tarfile.open(fname) as tar:
-        tar.extractall(path=tmp_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(tar, path=tmp_dir)
     for root, _, files in os.walk(tmp_dir):
         fnames += [os.path.join(root, fname) for fname in files]