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

cad

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Python modeling scripts and the cadgen utility to generate geometry, perform exports, and run validation checks.
  • [EXTERNAL_DOWNLOADS]: Fetches the cadgen tool (version 0.7.20) from the PyPI registry using the uvx package manager. This is a standard dependency for the skill's vendor-specific functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface through the processing of external CAD documents and user-provided sketches.
  • Ingestion points: Files are ingested through read_scene and read_step functions in references/inspection-and-validation.md; visual references like PNG sketches are used for modeling interpretation.
  • Boundary markers: The instructions in references/cad-brief.md direct the agent to record meaningful assumptions and clarify missing information rather than blindly following embedded data.
  • Capability inventory: The skill can write and execute Python code, manage files in project directories, and launch a local web server for model viewing via cadgen viewer.
  • Sanitization: Parsing of 3D geometry is performed using the OpenCascade (OCP) kernel via the build123d framework, which naturally validates structural integrity during the modeling process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 12:31 AM