clean-code

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

• Third-party content exposure detected (high risk: 0.80). The skill's verification scripts include commands that accept a (e.g., lighthouse_audit.py <url> and playwright_runner.py <url>), which implies the agent will fetch and run audits against arbitrary public web pages and must read/parse that external output, exposing it to untrusted third‑party content.