66-crisis-playbook

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

• Third-party content exposure detected (medium risk: 0.30). The skill runtime path relies on a first-party workflow/report “15-social-listening” to detect and then process crises from social monitoring data (untrusted users’ posts/comments are thus ingested and used without selecting a specific outsider-authored item first), creating an indirect prompt-injection risk.