light-idea-generation
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.72). 该技能在“新颖性核验/核心撞车检查”阶段会运行 m01 的
light-literature-search(如search_normalize.py、snowball.py)去检索并读取外部网页/论文元数据与正文片段作为“最近邻工作”证据,属于公共 web/第三方学术内容被运行时喂入 LLM 上下文的间接提示注入风险路径。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata