performance-and-web-vitals

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Run a Lighthouse Audit" section explicitly instructs running lighthouse against arbitrary public URLs (e.g., npx lighthouse https://example.com), which means the agent would fetch and interpret untrusted website content and audit results that can drive follow-up remediation decisions.