text-to-cad-harness
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires cloning a project skeleton from a public GitHub repository. Evidence: git clone https://github.com/earthtojake/text-to-cad.git
- [REMOTE_CODE_EXECUTION]: The environment setup process involves installing third-party dependencies from the NPM and PyPI registries. Evidence: pip install -r requirements-cad.txt and npm install.
- [COMMAND_EXECUTION]: The skill instructs the agent to manage local virtual environments and execute shell commands to run Python scripts. Evidence: ./.venv/bin/python models/bracket/bracket.py
- [COMMAND_EXECUTION]: The core logic of the skill involves the AI agent generating and executing Python code at runtime to produce CAD artifacts. Evidence: The workflow description involves agents editing and running files under the models directory.
Audit Metadata