statuspage

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md instructs the agent to fetch and act on public Statuspage content via Membrane (e.g., the "membrane request CONNECTION_ID /path/to/endpoint" and action run flows in the "Proxy requests" and "Running actions" sections), so external Statuspage/incident text is ingested into the agent's workflow and could influence subsequent decisions.