The Agent Skills Directory

[SAFE]: No malicious patterns were identified. The instructions are strictly limited to the stated purpose of SEO analysis.
[INDIRECT_PROMPT_INJECTION]: The skill recognizes that fetching external web pages introduces a risk of indirect prompt injection. It includes a specific security instruction for the agent to treat all fetched pages as untrusted data and to never follow instructions embedded in HTML, meta tags, or page copy. This proactive boundary marking is a security best practice.
[EXTERNAL_DOWNLOADS]: The skill references and suggests the use of well-known, trusted industry tools such as Google Search Console, PageSpeed Insights, and WebPageTest. These references are informative and used for diagnostic purposes, adhering to the trust-scope rules for well-known services.
[COMMAND_EXECUTION]: While the skill mentions using curl or browser-based developer tools, these are standard methods for fetching and inspecting the public source code of websites during an audit. No dangerous or unauthorized shell command execution was found.

seo-audit