cwv-audit
Warn
Audited by Snyk on May 2, 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 skill explicitly instructs the agent to pull and interpret real-world data from public third-party sources — e.g., the Chrome UX Report (CrUX) BigQuery queries and competitor-origin queries in the "CrUX BigQuery Queries" section (and the instruction to use Search Console/GA4 to pull site data) — which the agent would read and use to drive analysis and recommendations.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata