The Agent Skills Directory

[SAFE]: The skill's primary content is instructional and educational, guiding users or agents through an SEO audit process without including any executable code or scripts.\n- [COMMAND_EXECUTION]: The documentation mentions a standard shell command (grep) as a manual verification step for checking internal links. This does not constitute a risk as it is a read-only search operation on local project files.\n- [DATA_EXFILTRATION]: No network operations, exfiltration patterns, or connections to untrusted external domains were detected. All described audit activities are restricted to local file analysis.\n- [PROMPT_INJECTION]: The skill processes untrusted content from documentation files (Ingestion points: /docs/concepts/*.mdx). While boundary markers are absent, the skill's capabilities are limited to generating a text-based audit report (Capability inventory: Text generation), which does not present a path for privilege escalation or remote execution.

seo-review