blender-modeling-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute the Blender CLI with a Python script produced by the agent, as documented in the 'Execute and inspect' section of SKILL.md.
- [DYNAMIC_EXECUTION]: The core functionality involves the runtime generation and execution of a local Python script (create_asset.py) within the Blender environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions and technical requirements to generate code, creating an attack surface.
- Ingestion points: User asset requests and visual feedback descriptions in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill enables execution of the Blender binary with Python scripts.
- Sanitization: The instructions do not define methods for validating or escaping user input during code generation.
Audit Metadata