opennews-mcp-news-aggregation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and processes public third-party articles (see "Data Sources Overview" which lists Twitter/X and Telegram among sources) and the required runtime workflow (the subscribe_latest_news WebSocket usage and the "news.update" message format containing "content" and "ai_signal") has the agent read that untrusted content and act on it for trading/decisioning.