task-list

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests only the outsider’s request text when the agent calls the tasks tool (e.g., tasks(operation="add_multiple", content="...")) to store user-provided step strings as task content, which the tasks.py script then parses and persists from CLI args and includes when listing/completing tasks.