unitree-robot
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements robot control through a structured adapter architecture. Commands are parsed using restrictive regular expressions in
skill.py, which prevents arbitrary command execution or prompt injection by ensuring only predefined actions are performed. - [SAFE]: Dependencies are limited to
numpy, a well-known and trusted library for numerical computation, as specified inpyproject.tomland_meta.json. - [SAFE]: No hardcoded credentials, sensitive file access, or unauthorized network operations were detected. All external references point to the official resources of the author, LooperRobotics.
Audit Metadata