seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external websites which could contain malicious instructions. Ingestion points: HTML content, robots.txt, and sitemap.xml fetched via WebFetch. Boundary markers: None. The skill lacks instructions to ignore malicious commands embedded in audited site data. Capability inventory: Capability to read local project files and execute network requests to external APIs. Sanitization: None. Data from external sources is parsed and used directly in the audit report.
- [EXTERNAL_DOWNLOADS]: The skill connects to Google's PageSpeed Insights API (googleapis.com) to gather performance data.
Audit Metadata