qa-investigator
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Phase 2 的每個問題會在 agent prompt 中要求「用 WebSearch/WebFetch 查找更深入的資訊」,因此在運行時會抓取/讀取外部網頁內容(OUTSIDER:公共網路內容)並把其可讀文字注入到 agent/LLM 上下文。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata