The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or supporting documentation.
[PROMPT_INJECTION]: The skill explicitly warns against indirect prompt injection, instructing the agent to treat fetched web pages as untrusted data and to ignore any instructions embedded in HTML, meta tags, or page copy.
[COMMAND_EXECUTION]: The skill utilizes standard tools like curl and web_fetch for retrieving robots.txt files and HTTP headers. These are used strictly for technical SEO auditing purposes without evidence of shell piping or unsafe argument injection.
[EXTERNAL_DOWNLOADS]: The references provided point to official documentation from trusted organizations such as Google and Vercel, as well as well-known SEO industry authorities. These links are for informational purposes and do not involve remote code execution.

seo-audit