urdf-mjcf-to-usd-conversion

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes robot description files (URDF and MJCF) that are XML-based. If these files are sourced from untrusted locations or external ROS 2 nodes, they could contain instructions hidden in comments or metadata designed to influence the agent's behavior.
  • Ingestion points: External URDF/MJCF files and ROS 2 robot_description parameters are ingested as shown in SKILL.md and scripts/urdf_importer_ros.py.
  • Boundary markers: There are no specific boundary markers or instructions to the agent to disregard embedded content within the imported XML data.
  • Capability inventory: The skill uses run_script(), system shell commands (xacro, python.sh), and performs file system writes to output USD assets.
  • Sanitization: The provided scripts and instructions do not include sanitization or validation of the input XML content beyond standard API parsing.
  • [COMMAND_EXECUTION]: The skill requires the execution of shell commands and internal scripts to perform its primary conversion tasks. While this is expected behavior for a conversion tool, it provides a functional surface for executing powerful operations like xacro expansion and standalone simulator scripts.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the xacro package via pip and references several isaacsim standalone wheels. These are standard industry tools and vendor-provided resources related to the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 08:14 AM