chef
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). 该 skill 的运行时“走菜/冷启动/营养查询”等流程在未命中本地数据时会调用
scripts/fetch.py从外部网页/站点抓取食谱正文(如 xiachufang/allrecipes/bbcgoodfood 等),这些外部站点的可读文本会被写入data/recipes/*.md并随后由walkthrough.py读入进入 LLM 上下文,属于公共网页内容→LLM 的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata