karpathy-guidelines

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions designed to guide AI behavior during coding, reviewing, or refactoring tasks.
  • [SAFE]: No tool invocations, shell commands, or network operations are present in the guidelines.
  • [SAFE]: No prompt injection patterns, obfuscation techniques, or persistence mechanisms were detected.
  • [SAFE]: The external link provided is a reference to a well-known public social media post for context and does not involve automated script execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 07:49 AM
Security Audit — agent-trust-hub — karpathy-guidelines