seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites (HTML, robots.txt, and sitemaps) as part of its core audit functionality. 1. Ingestion points: Website URLs processed via web_fetch and curl (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Read operations via fetching tools and browser analysis; write operations via audit report generation. 4. Sanitization: Absent. This creates a surface for indirect prompt injection, but the risk is aligned with the primary skill purpose.
- [SAFE]: The skill references legitimate, well-known services and trusted organizations such as Google and Bing for site validation. The included reference for writing detection provides standard editorial guidance without malicious intent.
Audit Metadata