seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides guidelines for technical and on-page SEO audits. All referenced tools (Google Search Console, PageSpeed Insights, Bing Webmaster Tools) and external testing URLs (search.google.com) are well-known, trusted services and organizations. No malicious behavior or obfuscation was detected.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it is designed to ingest and analyze external website content (referenced via tools like web_fetch) and local context files. This is consistent with its primary function as an SEO auditor.
- Ingestion points: Website URLs provided by users and local context files such as
.agents/product-marketing-context.md. - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore embedded instructions within the fetched HTML.
- Capability inventory: The skill's capabilities are limited to reading local documentation, fetching web content for analysis, and generating reports; it does not utilize arbitrary command execution or unauthorized network requests.
- Sanitization: No specific content sanitization or filtering logic is specified within the instructions.
Audit Metadata