patent-assistant
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该技能的“专利检索”运行时会通过
scripts/patent_search.py向外部公共站点(如 Google Patents/Lens/Baidu 学术等)发起 HTTP 请求并读取其返回的可读文本/JSON(例如 Google Patents 的abstract),再把这些摘要等内容拼入输出,进而可能进入代理/LLM上下文,属于公共网页/第三方内容注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata