The Agent Skills Directory

[COMMAND_EXECUTION]: The skill contains instructions for the agent to perform an environmental check using the ls command on specific directories (e.g., ~/.claude/skills/) to identify which companion skills are currently installed. This is a discovery mechanism intended to suggest relevant additional tools to the user.
[REMOTE_CODE_EXECUTION]: The documentation provides standard installation commands using npx skills add. This is the designated method for adding skills to supported AI agents and does not represent an unauthorized execution vulnerability.
[PROMPT_INJECTION]: The instructions include a role-play directive to start responses with a specific emoji (🧢). This is a benign stylistic instruction and does not attempt to bypass safety filters or override core agent behavior.

game-balancing