Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only programmatic SEO guidance skill with no evidence of hidden execution, persistence, credential handling, or destructive behavior.
Before installing, understand that this skill is for planning SEO pages at scale. It may read a local product-marketing context file if one exists, and its trigger is broad enough that some general SEO or landing-page requests might invoke it, but no hidden execution or sensitive access was found.
The description says to use the skill whenever someone wants to create many similar pages targeting different keywords or locations, which is broader than the specific programmatic SEO phrases listed earlier. That broad condition lacks clear constraints or exclusion examples, so it may overlap with ordinary content-planning or landing-page requests that are not truly programmatic SEO.
The eval explicitly rewards the skill for 'triggering on casual phrasing' for broad requests about ranking for integrations, but it does not define tighter boundaries to distinguish strategy requests from adjacent SEO, product marketing, or technical audit tasks. Over-broad activation conditions can cause the wrong skill to be selected, leading to misrouting of user requests and advice that omits necessary safeguards or more appropriate specialist workflows.
The 'Translations' section instructs producing the same content in multiple languages and gives examples in Spanish, German, and Japanese. Because SQP-3 applies to natural-language locale policy concerns, this can be read as endorsing language targeting without any mention of user choice, opt-in, or region-specific justification.
No suspicious patterns detected.
