creature-artist
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data access patterns were detected. The skill primarily consists of instructional markdown files and anatomical guides.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process user-supplied images and concepts for modeling references.
- Ingestion points: Found in
references/asset-pipeline.md, which instructs the agent to process user-attached photos or concepts. - Boundary markers: None explicitly defined in the provided files to separate user-provided content from system instructions.
- Capability inventory: The skill uses Blender MCP integration for armature creation, mesh modeling, and viewport screenshots (
get_viewport_screenshot). - Sanitization: There are no explicit sanitization or filtering steps defined for external content within the skill instructions.
Audit Metadata