karpathy-guidelines
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text aimed at improving the quality and maintainability of code produced by the agent. No malicious patterns or technical vulnerabilities were identified.
- [NO_CODE]: The skill contains no executable scripts, binaries, or command-line instructions.
- [PROMPT_INJECTION]: The instructions provide standard professional guidance for coding tasks and do not attempt to bypass safety guardrails or subvert agent behavior.
- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files, environment variables, or perform network operations.
Audit Metadata