caveman
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a communication style guide that instructs the agent to use 'caveman' grammar (omitting articles and filler words) to save tokens. These instructions are purely stylistic and do not attempt to bypass safety filters or override core agent behavior.
- [SAFE]: No instances of data exfiltration, credential exposure, or malicious command execution were detected. The skill references local configuration files and logs (e.g., scripts/bp-config.sh) which are consistent with its described integration into a development workflow.
- [SAFE]: No obfuscation, dynamic code execution, or unauthorized remote downloads were found in the provided content.
Audit Metadata