blender-laser

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to send Python code to a local listener via curl at localhost:5656. This is a standard mechanism for AI agents to interact with local application bridges and is restricted to the local host.
  • [SAFE]: The provided Python scripts utilize official Blender API modules (bpy, mathutils, bmesh) for geometric raycasting and scene object management. No unauthorized file access, network exfiltration, or obfuscation was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 10:58 AM
Security Audit — agent-trust-hub — blender-laser