multi-source-inquiry
Warn
Audited by Snyk on May 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Yes — the "广度搜索" step explicitly requires using web search and content extraction/crawling tools (e.g., "网页搜索工具", "内容提取/抓取工具") and to ingest and summarize results/URLs for cross‑validation and decision‑making, which clearly pulls untrusted public third‑party content into the agent's workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata