ai-brand-consistency-checker
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). 该技能在运行时会接收用户提供的
materialUrl(公开页面链接)并在“contextComposer”模式下把其内容/页面文本纳入 LLM 上下文进行品牌一致性分析,因此存在来自外部网页的自由文本(潜在提示注入)进入上下文的路径。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata