caveman
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of behavioral instructions for stylistic persona adoption without any functional code, network access, or file system interactions.
- [PROMPT_INJECTION]: The instructions establish a persona focused on token efficiency. It explicitly includes safety rules (Auto-Clarity) that mandate a revert to standard prose for security-critical communications, preventing the persona from interfering with the clear delivery of warnings or confirmation prompts.
- [DATA_EXFILTRATION]: No mechanisms for data collection, credential access, or external communication are present.
- [COMMAND_EXECUTION]: The skill does not contain or request the execution of any system commands or external scripts.
Audit Metadata