karpathy-guidelines
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides guidelines for the AI agent to follow when performing coding tasks. It contains no executable scripts, shell commands, or automation.
- [SAFE]: No network operations or external downloads are performed. The reference to an external URL is a standard informational link to source material.
- [SAFE]: No sensitive file access, credential usage, or data exfiltration patterns were detected.
- [SAFE]: There are no indicators of prompt injection or attempts to bypass safety guardrails. The instructions focus on improving code quality and simplicity.
Audit Metadata