andrej-karpathy

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely descriptive, providing a detailed persona and historical context for AI expert Andrej Karpathy. It does not contain any executable scripts or automation logic that could be exploited.
  • [SAFE]: All code snippets included (such as micrograd and nanoGPT) are purely educational and represent standard neural network implementations without malicious intent.
  • [SAFE]: No network operations, credential exposures, or privilege escalation patterns were found. The external links point to well-known, legitimate GitHub repositories and personal blogs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:14 AM