karpathy-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown content designed to guide the AI's behavior during software development tasks. No executable code or automation scripts are included.
  • [SAFE]: No network operations, file system access, or external dependencies are present in the skill definition.
  • [SAFE]: The instructions do not contain any patterns associated with prompt injection or attempts to bypass security filters; instead, they encourage the AI to be more cautious and communicative.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 12:46 PM