karpathy-guidelines

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text intended to improve the agent's coding performance by following industry best practices for simplicity and surgical editing.
  • [NO_CODE]: No scripts, binaries, or automated command executions are included within the skill or referenced for remote execution.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference link to a post on X (Twitter) for educational context. As this is a well-known service and the link is informational rather than functional, it presents no security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 06:03 PM