hackernews

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and parse user-generated stories, comments, and user profiles from the public Hacker News API at https://hacker-news.firebaseio.com/v0 (e.g., "Get Top Stories", "Get Story/Comment/Job Details", "Get User Profile"), so untrusted third-party content is read and used to drive selection/filtering and subsequent actions.