blender-scripting
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run Blender scripts. Evidence: 'blender --background --python script.py'. Mitigation: Ensure scripts are generated from trusted templates and avoid direct interpolation of untrusted strings.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of external 3D files. 1. Ingestion points: File import operators such as 'bpy.ops.wm.obj_import'. 2. Boundary markers: None present. 3. Capability inventory: Command execution and file system access. 4. Sanitization: None.
- [EXTERNAL_DOWNLOADS]: The skill refers to official system package managers for installation. Evidence: 'apt' and 'brew' instructions in the compatibility section. Mitigation: Users should verify the integrity of packages from their system repositories.
Audit Metadata