monitor

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

• Third-party content exposure detected (high risk: 0.90). The skill's incident playbooks explicitly tell the agent to check and read third-party public monitoring/status pages and dashboards (e.g., "Check platform status page (Vercel/Netlify)", "Go to pagespeed.web.dev", and "Open error tracking dashboard (Sentry)" / "Read error message and stack trace"), so it ingests public third-party content that can change decisions like rollback vs wait.