The Agent Skills Directory

[SAFE]: The skill operates entirely locally, using a Python script (scripts/dfam_tool.py) to measure geometry facts from 3D mesh files (.stl, .obj, .3mf). It does not perform any network operations, access sensitive file paths, or store credentials.
[COMMAND_EXECUTION]: The skill requires the agent to execute a local Python script to perform measurements. This is a standard and intended function of the skill, used to extract numeric geometry data (volume, surface area, wall thickness, overhang angles).
[EXTERNAL_DOWNLOADS]: The requirements.txt file specifies standard, well-known scientific libraries including trimesh, numpy, rtree, scipy, networkx, and lxml. These are established packages used for geometry processing and do not pose a security risk in this context.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data (mesh files), the dfam_tool.py script acts as a sanitization layer by converting raw file content into structured numeric JSON data. This prevents instructions potentially hidden in mesh metadata from reaching the agent's reasoning context.

dfam-check