skills/earthtojake/text-to-cad/urdf/Gen Agent Trust Hub

urdf

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The script scripts/gen_urdf/cli.py performs dynamic code execution by loading Python modules from file paths passed as CLI arguments. It uses importlib.util.spec_from_file_location and module_spec.loader.exec_module(module) to run the gen_urdf() function defined in those files.\n- [COMMAND_EXECUTION]: The skill's workflow requires the agent to execute the Python interpreter to run the URDF generation and validation tools provided in the scripts/ directory.\n- [EXTERNAL_DOWNLOADS]: The skill depends on the yourdfpy package from PyPI, as specified in requirements.txt, for performing robot description validation.\n- [PROMPT_INJECTION]: The skill reads and processes Python and URDF files from the workspace, creating an indirect prompt injection surface where malicious data could influence agent behavior or execute unwanted code.\n
  • Ingestion points: Reads local .py generator scripts and .urdf XML files.\n
  • Boundary markers: None identified; input files are parsed or executed without explicit delimiters or instructions to ignore embedded content.\n
  • Capability inventory: Includes dynamic Python execution and filesystem write operations.\n
  • Sanitization: Performs XML structure and kinematic validation but lacks sanitization for the executable logic within input scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:13 PM
Security Audit — agent-trust-hub — urdf