seo-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill's URL-only mode and Tool Decision Tree explicitly instruct the agent to fetch and render arbitrary public webpages and resources (e.g., web_fetch , web_fetch /robots.txt, web_fetch sitemap.xml, web_search, and browser snapshot/document.querySelectorAll('script[type="application/ld+json"]')), so the agent will read untrusted third‑party content that directly influences audit decisions and tool usage, creating a clear avenue for indirect prompt injection.