isaaclab-using-sensors-actuators
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected. The skill instructions focus entirely on legitimate configuration and development workflows for the Isaac Lab environment.
- [COMMAND_EXECUTION]: The skill references a local validation command (
uv run --no-project python tools/skills/cli.py check). This is a standard project-internal utility used by developers to verify skill metadata and consistency, posing no external security risk. - [INDIRECT_PROMPT_INJECTION]: The skill describes workflows that ingest external data, such as terrain mesh paths and robot asset configurations. While these represent data ingestion surfaces, they are fundamental components of robotics simulation and are handled within the context of developer-defined task configurations rather than untrusted user-supplied strings, effectively mitigating risk.
- [EXTERNAL_DOWNLOADS]: All references in the skill target local documentation (
.rstfiles) and internal repository examples (source/isaaclab_tasks/). No external network requests or remote code downloads were identified.
Audit Metadata