blender-data-geometry
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities were identified. The skill implements strong input validation for all data ingestion.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill's operations are confined to the local Blender environment. There is no evidence of unauthorized file access or network communication.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data at several points including geometry vertices and text strings. However, the attack surface is mitigated by strict input validation defined in tools.yaml, which enforces numeric ranges, coordinate bounds, and character limits (ASCII-only, 160 char max). Boundary markers in SKILL.md explicitly restrict inputs to explicit data and forbid code execution.
- [UNVERIFIABLE_DEPENDENCIES]: All Python scripts utilize libraries belonging to the vendor ecosystem (dcc_mcp_core and dcc_mcp_blender), which is consistent with the skill's authoring context.
Audit Metadata