caveman
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and defines a specific communication style ('caveman mode') aimed at reducing token usage. It does not perform any technical operations, and it explicitly instructs the agent to revert to normal prose for security-sensitive contexts like credential exposure warnings.
- [NO_CODE]: The skill consists entirely of markdown instructions. There are no associated scripts, binaries, or configuration files that could be used for malicious execution.
- [DATA_EXPOSURE]: There are no indicators of data collection or exfiltration. The skill focuses solely on the transformation of the agent's output text.
- [REMOTE_CODE_EXECUTION]: The skill contains no package manager commands (npm, pip) or network requests (curl, wget) that would lead to the execution of remote code.
Audit Metadata