trigger-authoring-chat-agent

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

• Third-party content exposure detected (medium risk: 0.30). The chat.agent runtime ingests the conversation text via run: async ({ messages ... }) where messages are derived from the frontend sendMessage({ text }) history transported through useTriggerChatTransport, meaning outsider-authored user chat messages flow directly into streamText({ ...chat.toStreamTextOptions(), messages }).