The Agent Skills Directory

[SAFE]: The skill performs legitimate SEO audit functions using standard agent capabilities. It includes comprehensive documentation for international SEO and content quality assessment.
[PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites provided by the user via web_fetch and curl. While this is necessary for its primary function as an SEO auditor, it presents a theoretical surface for indirect prompt injection if an audited site contains malicious instructions. However, given the diagnostic nature of the skill and lack of high-privilege write operations, the risk is negligible. Ingestion points: External URLs retrieved via web_fetch and curl. Boundary markers: None explicitly defined in the skill instructions for delimited external content. Capability inventory: Read access to project context files (e.g., .agents/product-marketing.md), network operations (web_fetch, curl), and browser-based rendering for schema detection. Sanitization: No explicit sanitization or validation of external content mentioned in the instructions.

seo-audit