The Agent Skills Directory

[COMMAND_EXECUTION]: The render-scad.sh script executes the openscad binary using bash arrays ("${CMD[@]}"). This implementation prevents shell injection vulnerabilities by ensuring that user-provided arguments (like filenames or camera parameters) are treated as literal strings rather than executable code.- [INDIRECT_PROMPT_INJECTION]: The skill processes external .scad files which represents a potential attack surface for indirect prompt injection if the processed content or its visual output were to contain malicious instructions for the agent.
Ingestion points: The skill accepts a .scad file path as input through the INPUT variable in render-scad.sh.
Boundary markers: The skill does not employ specific boundary markers or 'ignore' instructions for the content of the SCAD files.
Capability inventory: The skill uses the Bash tool to run the rendering script and the Read tool to inspect results.
Sanitization: The script performs basic file existence checks but does not sanitize the internal content of the SCAD file before passing it to the openscad binary.

preview-scad