async-interview

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly instructs the agent to fetch and proxy data from the third-party Async Interview API (e.g., via "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint" and actions like "list-interview-responses"/"get-interview-response"), which returns user-generated candidate content that the agent is expected to read and could materially influence follow-up actions.