Adding tarfile member sanitization to extractall()

audiomate/corpus/io/voxforge.py

@@ -109,7 +109,26 @@ def extract_files(file_paths, target_path):
 
         for file_path in file_paths:
             with tarfile.open(file_path, 'r') as archive:
-                archive.extractall(target_path)
+                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(archive, target_path)
 
             file_name = os.path.splitext(os.path.basename(file_path))[0]
             extracted.append(os.path.join(target_path, file_name))

audiomate/utils/download.py

@@ -139,4 +139,26 @@ def extract_tar(tar_path, target_folder):
     ``target_folder``.
     """
     with tarfile.open(tar_path, 'r') as archive:
-        archive.extractall(target_folder)
+
+        import os
+
+        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(archive, target_folder)