Adding tarfile member sanitization to extractall() (#508)

amlb/datasets/fileutils.py

@@ -96,5 +96,24 @@ def unarchive_file(path, dest_folder=None):
             zf.extractall(path=dest_folder)
     elif tarfile.is_tarfile(path):
         with tarfile.open(path) as tf:
-            tf.extractall(path=dest_folder)
+            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(tf, path=dest_folder)
     return dest