opennews
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public news and social media content via the OpenNews API (e.g., POST /open/news_search and GET /open/free_hot), pulling article text, links, and tweets from untrusted sources like Twitter/X, Telegram, Weibo and news sites and using those items and AI ratings to generate signals and summaries, so that third‑party content can materially influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata