hackernews

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches public, user-generated Hacker News content from https://hacker-news.firebaseio.com/v0 (e.g., /topstories.json and /item/{id}.json) and instructs the agent to read story text, comments, and user bios as part of its workflow, so untrusted third-party content could influence subsequent actions.