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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 27, 2026, 07:09 AM
Issues
1
Security Audit — snyk — chef