web-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly takes arbitrary live site URLs from the user and runs Lighthouse and Playwright audits (see SKILL.md: "The user provides: the URL of the site to audit" and the Lighthouse/Playwright commands), so untrusted third‑party web content is fetched, analyzed, and can directly influence the agent's findings and subsequent actions.