mirror of
				https://github.com/clearml/clearml
				synced 2025-06-26 18:16:07 +00:00 
			
		
		
		
	Adding tarfile member sanitization to extractall() (#803)
This commit is contained in:
		
							parent
							
								
									b598ee5866
								
							
						
					
					
						commit
						d17903d4e9
					
				| @ -165,10 +165,48 @@ class StorageManager(object): | ||||
|                 ZipFile(cached_file.as_posix()).extractall(path=temp_target_folder.as_posix()) | ||||
|             elif suffix == ".tar.gz": | ||||
|                 with tarfile.open(cached_file.as_posix()) as file: | ||||
|                     file.extractall(temp_target_folder.as_posix()) | ||||
|                     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(file, temp_target_folder.as_posix()) | ||||
|             elif suffix == ".tgz": | ||||
|                 with tarfile.open(cached_file.as_posix(), mode='r:gz') as file: | ||||
|                     file.extractall(temp_target_folder.as_posix()) | ||||
|                     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(file, temp_target_folder.as_posix()) | ||||
| 
 | ||||
|             if temp_target_folder != target_folder: | ||||
|                 # we assume we will have such folder if we already extract the file | ||||
|  | ||||
		Loading…
	
		Reference in New Issue
	
	Block a user