isaaclab-diagnosing-joint-poses
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and referenced local scripts indicates they are intended for legitimate robotics simulation development workflows within the Isaac Lab ecosystem.
- [COMMAND_EXECUTION]: The skill includes a validation step using a local command (
uv run --no-project python tools/skills/cli.py check). This is a standard development practice for validating skill integrity within the project's own repository structure. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to interpret natural language requests (e.g., "gripper fingers down") to identify robot pose requirements. The workflow mitigates risks by incorporating state-based measurement and validation (e.g., body-axis dot products, joint limit checks) rather than relying solely on visual interpretation or unvalidated inputs.
Audit Metadata