wechat-article-search
Warn
Audited by Snyk on Jun 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该技能在运行时会通过
httpGet()抓取外部网页(如https://weixin.sogou.com/weixin?...),再用cheerio从返回的 HTML 中提取title/summary/source等文本并作为结果对象返回;这些文本属于“公共网页内容(搜狗微信搜索页)”的外部作者内容,随后会被上层流程喂入 LLM 上下文(间接提示注入风险)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata