seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework involves ingesting untrusted content from external websites, which presents an indirect prompt injection surface.
- Ingestion points: Processes external data from target sites, including
Robots.txt,XML Sitemaps, and HTML metadata (titles, descriptions, headings) as specified inSKILL.md. - Boundary markers: Lacks explicit delimiters or instructions to ignore commands embedded within the external data.
- Capability inventory: Instructs the agent to review and diagnose issues using its file-reading and analysis capabilities.
- Sanitization: Provides no instructions for sanitizing or filtering the content obtained from audited sites.
Audit Metadata