triage

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

• Third-party content exposure detected (high risk: 0.90). This skill programmatically fetches and parses external, potentially untrusted content from public services (Sentry via scripts/check_sentry.sh and generate_postmortem.sh, Vercel via scripts/check_vercel_logs.sh, GitHub CI via scripts/check_github_ci.sh, and arbitrary production URLs via scripts/check_health_endpoints.sh / HEALTH_ENDPOINTS), and that content is read and used to drive investigation/fix actions—meeting the criteria for indirect prompt injection risk.