blender-scripting
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the blender command-line interface to run Python scripts headlessly. This is the standard and intended method for automating 3D tasks and does not involve any unauthorized command execution.
- [PRIVILEGE_ESCALATION]: The instructions mention 'sudo apt install' for initial software setup on Linux. This is a legitimate installation step and is not used by the skill during its operational runtime.
- [INDIRECT_PROMPT_INJECTION]: The skill has the capability to ingest and process external 3D files (e.g., .blend, .obj). 1. Ingestion points: File paths provided to bpy.ops.wm.open_mainfile and various import operators in SKILL.md. 2. Boundary markers: Not applicable for binary/structured 3D data formats. 3. Capability inventory: Shell command execution for Blender CLI and local file system writes in SKILL.md. 4. Sanitization: Not present, though the risk is low due to the nature of the data and lack of network access.
Audit Metadata