Merge pull request #1835 from TrellixVulnTeam/main

CVE-2007-4559 Patch

recommenders/datasets/criteo.py

@@ -157,7 +157,26 @@ def extract_criteo(size, compressed_file, path=None):
         extracted_dir = path
 
     with tarfile.open(compressed_file) as tar:
-        tar.extractall(extracted_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, extracted_dir)
 
     filename_selector = {"sample": "dac_sample.txt", "full": "train.txt"}
     return os.path.join(extracted_dir, filename_selector[size])