juicebox-incident-runbook

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

• Third-party content exposure detected (high risk: 1.00). The runbook explicitly instructs fetching public Juicebox endpoints (e.g., curl https://status.juicebox.ai/api/status and calls to https://api.juicebox.ai in Quick Diagnostics and Response Procedures) and uses those external responses to decide actions (enable fallback, rotate keys, restart deployments), so untrusted third-party content can materially influence agent behavior.