research-analyst-system
Warn
Audited by Snyk on Mar 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The workflow's "并行研究(研究员执行)" step explicitly instructs researchers to call external search tools ("必要时调用搜索工具(WebSearch / MCP PubMed / metaso 等)") so the agent will fetch and read public third‑party web content and use it to generate and influence research reports.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata