seo-audit

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly directs the agent to fetch and render public webpages (mentions web_fetch and curl, using a browser tool to run document.querySelectorAll on pages, and external tests like Google Rich Results Test / Screaming Frog) so the agent will read and interpret untrusted third‑party site content as part of its audit workflow, which could carry embedded instructions.