diagnose-seo
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and review public site resources (e.g., "[domain]/robots.txt" and XML sitemap URLs" in "Layer 1: Crawlability" and to inspect page HTML/headers/JS-rendered content in "Layer 3: Renderability"), which are untrusted, user-controlled third‑party web content the agent must interpret and that can directly influence diagnostic actions.
Audit Metadata