seo-technical
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external website data (such as robots.txt, HTML source, and meta tags). This creates a theoretical surface for indirect prompt injection if the content of the site being audited contains malicious instructions designed to influence the agent's behavior. However, this risk is inherent to the intended primary purpose of the skill.\n
- Ingestion points: External website content processed during technical SEO audits (robots.txt, sitemaps, HTML tags).\n
- Boundary markers: None specified in the instructions for separating user intent from processed site data.\n
- Capability inventory: The skill utilizes third-party SEO audit tools (DataForSEO) to retrieve site metrics and data.\n
- Sanitization: No specific content sanitization or instruction-filtering steps are defined in the skill body.
Audit Metadata