seo-audit

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md Audit Framework explicitly instructs the agent to fetch and inspect public sites and resources (e.g., robots.txt, XML sitemap, site pages, "site:domain.com" checks, and using a browser tool or Google Rich Results Test with document.querySelectorAll to detect JSON‑LD), so the agent will consume untrusted third‑party web content that can materially influence audit decisions.