a11y-audit

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow executes automated scanners (pa11y/Lighthouse) and curl fetches against arbitrary Shopify store URLs supplied by the user, which can return outsider-authored storefront content and markup.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs and executes the dynamic fetching and execution of external packages (pa11y, lighthouse, @puppeteer/browsers) via npx during runtime setup and execution, representing an unverified operational dependency.