bkn-ontology-builder
Warn
Audited by Snyk on Jul 21, 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 Skill 的运行流程要求在 “Archive / Context” 中识别并“归档或登记输入”(来源包括 PRD/会议纪要/交接摘要/系统与数据材料等),随后由 LLM 的 Generator/Verifier 读取这些材料来生成与校验方案,因此若这些输入来自非操作用户(如他人撰写的 PRD/纪要/交接材料/外部文档),其自由文本会进入 LLM 上下文,构成间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata