karpathy-guidelines

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and behavioral guidelines for code generation tasks. It provides principles for thinking before coding, prioritizing simplicity, performing surgical changes, and using goal-driven execution.
  • [SAFE]: No suspicious network activity or data access patterns were identified. The only external link provided is for attribution to a public GitHub repository.
  • [SAFE]: The tool permissions defined in the frontmatter (Read, Glob, Grep) are standard for file system navigation and content analysis and are used appropriately for the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 10:09 AM
Security Audit — agent-trust-hub — karpathy-guidelines