andrej-karpathy

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of purely instructional markdown content. It establishes a set of behavioral guardrails for coding tasks such as refactoring and development.
  • [NO_CODE]: There are no executable scripts, shell commands, or dynamic code execution patterns within the skill files.
  • [EXTERNAL_DOWNLOADS]: The skill contains references to public documentation and source code on GitHub and X (formerly Twitter). These references are informational and do not involve the automated download or execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:07 AM
Security Audit — agent-trust-hub — andrej-karpathy