multi-model-writer

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly includes browser automation for web interfaces and advertises "Web research integration" (Gemini) and "Real-time X/Twitter" (Grok) and example commands like /write-grok "What's trending in cardiology on X right now?", which indicate it will fetch and ingest public social media/web content that the agent will read and interpret.