add-ai-chat-tool

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

• Third-party content exposure detected (medium risk: 0.30). At runtime, the chat agent’s tool-loop ingests the user’s free-text prompt that the model converts into tool calls, which are then dispatched to client or server tool handlers (e.g., src/apps/chats/hooks/useAiChat.ts and api/chat/tools/*).