isaaclab-selecting-backends
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides technical instructions for managing Isaac Lab simulation backends (PhysX and Newton). All code examples utilize local project scripts (e.g.,
scripts/environments/random_agent.py) and standard Isaac Lab CLI tools. - [COMMAND_EXECUTION]: The skill includes instructions for running local validation and training scripts via
uv run. These commands are standard for the intended workflow and do not involve untrusted remote sources or suspicious privilege escalation. - [REMOTE_CODE_EXECUTION]: No remote script downloads or execution patterns were identified. All references are to local documentation and repository-specific source files.
- [PROMPT_INJECTION]: The instructions and evaluation scenarios are focused on providing accurate technical guidance. There are no attempts to override agent safety protocols or bypass system constraints.
Audit Metadata