evaluating-cosmos-policy
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the primary policy code and simulator environments from public GitHub repositories, including the official NVIDIA Lab's cosmos-policy repository and a specific research fork of robocasa.\n- [COMMAND_EXECUTION]: The workflow involves standard shell commands for managing Python environments via uv, cloning repositories, and executing evaluation modules through python -m.\n- [SAFE]: The skill includes benign Python code to read and parse evaluation results from JSON log files generated locally during the simulation process.
Audit Metadata