trigger-event-detection

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests external public content—e.g., crunchbase_api.get_recent_funding in check_funding_events, linkedin_api.get_job_postings in check_hiring_signals, and the TRIGGER_SOURCES list (news_alerts, job_boards, linkedin_changes, etc.)—and then interprets those untrusted third-party signals to score triggers and drive outreach actions, so third‑party content can materially influence agent behavior.