ez-hn

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

• Third-party content exposure detected (high risk: 0.70). Yes — the skill directly fetches and processes user-generated Hacker News content from the public APIs (https://hacker-news.firebaseio.com/v0 and https://hn.algolia.com/api/v1) as shown in scripts/hn.py and SKILL.md, reading story/comment text and using search hits (objectID) to select and fetch further items, which exposes the agent to untrusted third‑party content.