hn-to-x-poster

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow directs the agent to read the Hacker News front page (https://news.ycombinator.com/) — a public, user-generated source — and use those front-page titles/context to decide which items to include and to build/post a Chinese message to X, so untrusted third-party content can directly influence the agent's actions.