blender-assets
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of Blender command-line operations to automate asset rendering and exports.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external .blend files, which serves as an ingestion point for untrusted data. The capability to execute Python scripts within the Blender environment provides a surface where data inside a malicious blend file could potentially influence agent behavior.
- Ingestion points: Processes .blend source files in the local workspace.
- Boundary markers: Absent for content within Blender data blocks.
- Capability inventory: Invokes shell commands (Blender executable) and executes Python scripts using the bpy API.
- Sanitization: Includes basic validation for file extensions and path resolution.
- [DYNAMIC_EXECUTION]: The skill uses Blender's internal Python interpreter to execute automation scripts, which is the standard and necessary method for programmatic Blender interaction.
Audit Metadata