news-aggregator-skill-3

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts (scripts/fetch_news.py) explicitly fetch and deep-fetch article text from public sites like Hacker News, Weibo, GitHub Trending, Product Hunt, 36Kr, Tencent, WallStreetCN, and V2EX, and SKILL.md requires the agent to perform mandatory "Deep Scan"/AI analysis on the fetched third‑party content, meaning untrusted/user-generated web content is ingested and directly influences analysis and subsequent actions.