wrk

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs using "membrane action run" and the "Proxy requests" flow (membrane request CONNECTION_ID /path/to/endpoint) to fetch data from the Wrk API, which can return untrusted/user-generated content that the agent would read and could influence subsequent actions.