benchmark
Warn
Audited by Snyk on Mar 24, 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). SKILL.md (Mode 1: Page Performance) explicitly says the agent will "Navigate to each target URL" and measure/inpect page resources and third-party scripts, meaning it fetches and interprets arbitrary public web pages whose untrusted content could influence measurements or downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata