The Agent Skills Directory

[SAFE]: The skill provides purely instructional content and frameworks for performing SEO audits. It does not include executable code, scripts, or external dependencies. All URLs referenced are legitimate SEO tools (e.g., Google Search Console, PageSpeed Insights) or internal references to other skills.
[DATA_EXFILTRATION]: There are no network operations that could exfiltrate data. The skill mentions using web_fetch and curl, but only in the context of analyzing public website data for SEO purposes, with clear warnings about the limitations of these tools (e.g., inability to see JavaScript-rendered schema).
[PROMPT_INJECTION]: The instructions are robust and focused on SEO expertise. There are no attempts to bypass safety filters or override agent behavior maliciously. The mention of 'AI Writing Detection' in the references is a legitimate content quality guideline to help users create more natural-sounding content.
[COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or dynamic code execution patterns. It provides a static framework for analysis.
[EXTERNAL_DOWNLOADS]: No external packages or scripts are downloaded or executed. All technical checks described (e.g., robots.txt, sitemaps) are standard web analysis procedures.

seo-audit