ai
Warn
Audited by Snyk on May 6, 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). references/agents/02-web-search.md (and the modified app/api/chat/route.ts) explicitly enables OpenRouter's ":online" web-search (modelId
${MODELS.balanced}:online), causing the agent to fetch and incorporate untrusted public web content into its responses and decision-making.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata