unity-smart
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, unauthorized data access, or suspicious command execution were detected in the skill definitions.
- [PROMPT_INJECTION]: The skill's instructions and descriptions do not contain any patterns aimed at overriding agent behavior or bypassing safety filters.
- [DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network communication patterns were found.
- [REMOTE_CODE_EXECUTION]: The skill defines operations for the Unity Editor environment (e.g., scene queries, layouts). There are no external dependencies, package installations, or remote script execution attempts.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-defined strings (e.g., property values, object names, and prefab paths), these are standard inputs for its intended purpose of Unity scene manipulation. No specific vulnerability to instruction injection via these fields was observed during static analysis.
Audit Metadata