ponytail-audit
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a specific instructional framework for the AI agent to analyze codebases for over-engineering. It does not include any executable code, scripts, or automated modification capabilities.
- [PROMPT_INJECTION]: The skill includes instructions to revert its behavior using specific commands like "stop ponytail-audit" or "normal mode". These are standard state management instructions for an agent and do not constitute a safety bypass or malicious prompt injection.
- [DATA_EXFILTRATION]: No network operations, external URLs, or data transmission patterns were found. The skill operates entirely within the agent's provided context.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or instructions to execute arbitrary code. It is designed for static analysis of provided text/code only.
Audit Metadata