The Agent Skills Directory

[SAFE] (SAFE): The skill consists entirely of markdown documentation and metadata. No executable scripts, network requests, or dangerous file operations are defined within the skill package.
[COMMAND_EXECUTION] (INFO): The file references/full-guide.md contains example shell commands (e.g., k6 run, node --prof) provided for educational purposes. These are not executed automatically by the skill.
[PROMPT_INJECTION] (LOW): The skill includes instructions to read external project files like ARCHITECTURE.md for context. While this is an indirect injection surface (Category 8), the skill lacks any automated high-privilege tools to exploit such an injection.

performance-expert