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
Risk Level
SAFE
Analyzed
Jun 29, 2026, 12:55 AM
Security Audit — agent-trust-hub — evaluating-cosmos-policy