aeon-hacker-news-digest

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

• Third-party content exposure detected (high risk: 0.95). At runtime the skill fetches Hacker News story/comment JSON from https://hacker-news.firebaseio.com/v0/item/${id}.json, then “mines” and quotes outsider-authored comment body text into the agent’s LLM context (public HN comments are written by non-operating users).