client-demo-portal
Warn
Audited by Snyk on Aug 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL 的运行路径是通过前端/后端将用户输入的检索/分析问题发送到外部 LLM(如 DeepSeek)并使用其返回文本渲染/生成结果(server.js 触发端点如 GET /api/search、POST /api/analyze 以及前端搜索/分析流程),因此外部用户可提交自由文本进入 LLM。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata