seo
Warn
Audited by Snyk on Mar 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and render public site pages (e.g., "use: Browser tool — render page and run: document.querySelectorAll('script[type="application/ld+json"]')", check robots.txt, XML sitemap, and perform site:domain.com/PageSpeed Insights checks), which requires ingesting untrusted public website content that the agent will read and act on as part of its audit workflow.
Audit Metadata