streamdown

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path is that the agent renders Markdown from children (e.g., msg.content / message.content from useChat()), which is outsider-authored free text (chat messages from other users/assistant) and is ingested into the LLM context via the chat/AI streaming flow.