The Agent Skills Directory

[SAFE]: No security issues detected. The skill focuses on adjusting the agent's output style for brevity and token efficiency. It does not contain any malicious patterns such as remote code execution, persistence mechanisms, or credential harvesting.- [PROMPT_INJECTION]: The instructions establish a stylistic persona and maintain its state across conversations. These instructions are benign and do not attempt to override safety protocols or extract system prompts.- [DATA_EXFILTRATION]: There are no commands or logic present that would allow for the access of sensitive files or the exfiltration of data to external servers. The 'Token Police' functionality is limited to calculating the length of user text and does not use any sensitive tools.

desert-mode