character-art-rig-weapon
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill does not contain instructions to bypass safety guidelines or override agent behavior. It includes rigorous 'Hard Rules' that lock protagonist identity and enforce a 'human-handoff' protocol, ensuring the user remains in control of the final output and game feel.
- [DATA_EXFILTRATION]: No network operations, API calls, or attempts to access sensitive system files (e.g., credentials, environment variables) were found. The skill operates strictly on local project assets and Unity-specific data structures like ScriptableObjects.
- [COMMAND_EXECUTION]: There is no evidence of shell command execution or subprocess spawning. The provided C# templates utilize standard Unity Engine APIs for character transformation and mesh manipulation.
- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It references official Unity documentation and project-specific files without providing functional or fabricated URLs that could lead to remote code execution.
- [CREDENTIALS_UNSAFE]: The skill does not contain or request hardcoded credentials, API keys, or private secrets. It encourages standard Unity practices for managing configuration data through ScriptableObjects.
Audit Metadata