fr3-duo-control

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automates the retrieval of high-fidelity robot models and assets from the official Google DeepMind GitHub repository (google-deepmind/mujoco_menagerie) to ensure simulation accuracy.
  • [COMMAND_EXECUTION]: Implements subprocess.run within its model-building scripts to perform sparse git clones and maintenance of required robot configuration assets.
  • [DYNAMIC_EXECUTION]: Utilizes importlib.import_module in scripts/bringup.py to verify the local Python environment and ensure that necessary dependencies like pylibfranka and mujoco are installed before proceeding with hardware control.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through config/robot_config.json and interactive measurement prompts in scripts/bringup.py. Boundary markers for these inputs are absent in the internal logic. The capability inventory includes subprocess execution for asset cloning, file system modification for logging and configuration, and low-level hardware actuation. The skill performs numeric validation and physical constraint checks on measurements to sanitize ingested measurement data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 03:07 AM