searchnews
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to crawl and extract full articles from public news sites (see "必抓源列表" with URLs like https://news.aibase.com/zh/daily, https://next.ithome.com/, https://36kr.com/ and the "深度检索" requirement to "逐条访问详情页"), which are untrusted third‑party web content that the agent must read and interpret as part of its workflow.
Audit Metadata