andrej-karpathy-perspective
Pass
Audited by Gen Agent Trust Hub on May 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a detailed intellectual framework and research data to simulate a specific personality. All external links point to legitimate, well-known technical blogs, interview platforms, and career-related news sites.
- [SAFE]: The 'Agentic Protocol' defined in
SKILL.mdencourages the agent to verify facts using search tools, which promotes accuracy in technical discussions. While fetching external data is a theoretical surface for indirect prompt injection, it is managed by the agent's internal safety guidelines and the specific scope of this personality skill. - [SAFE]: No obfuscation, data exfiltration, or unauthorized command execution patterns were found. The skill adheres to the platform's installation and configuration standards.
Audit Metadata