The Agent Skills Directory

[SAFE]: The skill provides a comprehensive and legitimate technical framework for SEO auditing, covering standard industry topics such as Core Web Vitals, robots.txt management, and security headers.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external websites via the WebFetch tool. This is the primary intended function, but it creates a theoretical surface where malicious content on a scanned website could attempt to influence the agent's output.
Ingestion points: The skill uses WebFetch to retrieve content from third-party websites for auditing purposes.
Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided for the fetched content.
Capability inventory: The skill is restricted to WebFetch (network read) and Read (file system read), limiting its potential impact.
Sanitization: No specific content sanitization or escaping instructions are present for the external data ingested.

30x-seo-technical