crisis-response-protocol

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

• Third-party content exposure detected (medium risk: 0.30). In src/lib/ai/chat-handler.ts, the runtime calls assessCrisisLevel(message, ...) and then uses the same message (user free text) when generating the AI response via generateAIResponse(message, systemPrompt), so outsider-authored chat content directly enters the LLM workflow.