prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly limited to an advisory role. It explicitly instructs the agent to analyze prompts and provide recommendations without executing any implementation tasks, writing code, or running commands. It specifically warns the agent: 'Your ONLY output is an analysis plus an optimized prompt.'
- [SAFE]: Project context detection is limited to reading standard configuration files (e.g., package.json, go.mod, pyproject.toml) to identify the technology stack. No attempts to access sensitive files like credentials, SSH keys, or environment variables were detected.
- [SAFE]: The skill implements clear boundary instructions to prevent the agent from switching into implementation mode, even if requested by the user during the optimization process. It instructs the agent to redirect the user to a normal task request if they want execution.
- [SAFE]: No obfuscation, remote code execution, persistence mechanisms, or credential exfiltration patterns were identified.
Audit Metadata