ai-hr-performance-review
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
materialText/materialFile/materialUrl(其中materialUrl可能触发对公开网页的抓取与提取文本),这些文本属于非操作用户选择引入的外部自由文本来源,随后被拼入 LLM 上下文(contextComposer)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata