karpathy-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and markdown documentation designed to guide the agent's reasoning process.
- [SAFE]: No tools are authorized in the frontmatter (
allowed-tools: []), preventing the skill from executing commands or accessing the file system. - [SAFE]: There are no remote script downloads, package installations, or obfuscated patterns detected in the content.
Audit Metadata