urdf-sdf-model
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external robot model files (URDF, SDF, and meshes), which serves as an ingestion point for untrusted data. * Ingestion points: Reads model files from the filesystem via Read, Edit, and Glob tools as seen in SKILL.md and README.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed files are present. * Capability inventory: The skill has access to broad tools including Bash(*), Write, and Edit. * Sanitization: No sanitization or validation of the input file content is described before processing with shell commands.
- [EXTERNAL_DOWNLOADS]: The skill documentation references external packages and resources for extended functionality. * References the installation of the cadquery-mcp-server package via pip. * Provides links to external third-party services and repositories: github.com/bonninr/freecad_mcp, blender-mcp.com, playbooks.com, and mcpservers.org.
Audit Metadata