huashu-nuwa
Warn
Audited by Snyk on Jul 2, 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). 该Skill在 Phase 1 的“纯网络搜索/本地语料优先补充搜索”中会通过 WebSearch/网页抓取/字幕下载等工具把“公共网页/播客转录/社交媒体内容”等OUTSIDER文本读入并写入
references/research/*.md,随后这些md会进入 LLM 的后续提炼与生成上下文,形成间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata