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.pysnowball.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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 05:04 AM
Issues
1
Security Audit — snyk — light-idea-generation