implement-afk-agentic

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s required runtime path reads outsider-authored GitHub issue/ticket text (“issue tracker” and the ticket’s “Seams under test”/acceptance criteria) to decide whether to run AFK and to drive /tdd, so a third party can submit poison by posting to an issue labeled ready-for-agent.