alphai-twitter

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests public, user-generated X/Twitter content via the monitorList HTTP API and a WebSocket stream (see "数据获取方式" and the "工作流程"/examples in SKILL.md showing monitorList, WebSocket, x/search, x/tweets and twitter-search), and the agent is instructed to read and act on that content (extract contract addresses, run analyses, query tickers, push alerts), so third‑party content can materially influence tool use and actions and could enable indirect prompt injection.