ai-serp-analysis
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: 0.75). 该技能在运行时会接收用户提供的
materialUrl(公开网页/SERP/竞品链接)并在“contextComposer”模式下把页面内容作为可读文本注入 LLM 上下文;若该 URL 指向第三方网页,则属于“公共 web 内容在运行时被抓取/浏览器提取并喂给模型”的外部自由文本来源。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata