isaac-sim-robot-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external, potentially untrusted data which could be used to influence agent behavior if not properly handled.
  • Ingestion points: The skill specifies ingestion of occupancy maps (map.yaml), A* pathfinding data, and robot USD files converted from URDF/MJCF sources.
  • Boundary markers: Absent. There are no instructions or delimiters provided to separate untrusted external data from the agent's primary instructions.
  • Capability inventory: The skill employs powerful Omniverse Kit capabilities, including timeline control (timeline.play()), physics management (SimulationManager), and scene manipulation via the pxr (USD) library.
  • Sanitization: Absent. The instructions do not include validation or sanitization steps for the data received from external sources like the occupancy map or path planner.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:57 PM
Security Audit — agent-trust-hub — isaac-sim-robot-navigation