The Agent Skills Directory

[SAFE]: The skill is purely informational and instructional. It contains no executable scripts (Python, JavaScript, or Shell) and no instructions that attempt to bypass AI safety guidelines.
[DATA_EXPOSURE]: The skill instructs the agent to check for specific context files, such as .agents/product-marketing-context.md. This is a standard pattern for providing project-specific context to an agent and does not involve accessing sensitive system credentials or private user files.
[EXTERNAL_DOWNLOADS]: While the documentation mentions several SEO tools (e.g., Semrush, Ahrefs, ZipTie) and AI platforms (e.g., ChatGPT, Perplexity), these are listed as references for the user or as external services the agent may interact with via standard tools. There are no background downloads or unverified remote code execution patterns.

ai-seo