Streaming Mindmap Rendering

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

• Third-party content exposure detected (high risk: 0.90). The skill's startStreaming(url: string) calls fetch(url) and reads the response body stream which is cleaned and passed through plaintextToMindElixir to update the live mindmap, meaning the agent will read and interpret arbitrary/untrusted third-party URL content.