reconcile-roadmap

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow reads thread-root files (docs/threads/<...>/decisions.md, seed.md, proposal.md, and roadmap.md) authored by other parties (outsider thread contributors) and then uses their prose to edit/reconcile the roadmap, so outsider-authored free text can enter the agent’s LLM context via the “Load the authority” step.