crisis-communications

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs checking external wire services and monitoring social media (see "Immediate actions (0-10 min)" — "Check wire services (AP, Reuters, AFP)" and the "Social media crisis response" / CrisisMonitor sections that ingest platform/content/author fields), meaning the agent is expected to ingest untrusted public/user-generated content that can materially influence verification and response decisions.