xiaohongshu-fetch
Warn
Audited by Snyk on Jul 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). SKILL.md 的运行路径会先用
scripts/fetch.py从“用户提供的小红书笔记链接”抓取网页并解析window.__INITIAL_STATE__,把其中的标题/正文/作者/字幕/图片OCR等内容(均为外部作者的文本)写入本地.txt/.json后再由 LLM 读取到上下文;因此存在“公共网页/外部内容 → LLM读取”的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata