tech-route-comparison
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs performing public web/academic searches and reading external pages/PDFs using channels like Exa, Tavily, Brave, "web" search and URL readers (e.g., Jina) as part of evidence collection (see "工具路由与降级策略" and references/source-routing.md), so untrusted third-party content from the open web can be ingested and materially influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata