laohan-chuangzuo
Warn
Audited by Snyk on Jun 12, 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 在运行时会执行 Pre-B 的 URL 抓取(“根据平台自动选择方法…保存为 output/content-YYYY-MM-DD.md,进入素材模式”),这些网页正文属于“公共 web content fetched at runtime”,会被后续 Step 1 读入并进入 LLM 上下文进行 Layer A/B 整理。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata