case-retrieval
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 (medium risk: 0.65). 该技能在运行时会调用外部“案例检索”工具(如北大法宝 MCP)获取司法案例的可读文本/裁判要旨并写入LLM上下文用于相似度评估与报告生成;这些案例内容属于第三方(非操作用户选择引入的)公开/数据库来源的文本,因此存在间接提示注入风险。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's README explicitly requires calling the remote MCP case-retrieval service at URLs such as https://mcp.pkulaw.com (and the runtime apim endpoint pattern https://apim-gw.pkulaw.com/{SERVICE_ID}/mcp) to fetch case data that is injected into the agent's context as the authoritative search results, so this runtime external content directly controls the agent's outputs and is a required dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata