autonomous-modeling

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No injection patterns, role-play bypasses, or instructions to ignore safety guidelines were detected. The trigger phrases and workflow are strictly focused on 3D modeling tasks.
  • [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive local file paths (e.g., .ssh, .aws) were found. The skill's operations are confined to the Blender environment state.
  • [REMOTE_CODE_EXECUTION]: There are no patterns of downloading and executing remote scripts or installing unverified packages. The 'script-based creation' mentioned in the description refers to the internal use of Blender's Python API through controlled tool interfaces.
  • [COMMAND_EXECUTION]: The skill does not use shell commands or subprocesses to interact with the host operating system. All actions are performed through defined Blender MCP tools.
  • [OBFUSCATION]: The content is clear and uses plain text instructions. No hidden characters, Base64 encoding, or homoglyph attacks were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:09 AM
Security Audit — agent-trust-hub — autonomous-modeling