unity-gameobject
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Data is pulled from the Unity scene via gameobject_find and gameobject_get_info in SKILL.md. Boundary markers: The instructions do not require the agent to isolate or treat environment-derived strings as untrusted. Capability inventory: The skill enables high-impact actions like gameobject_delete, gameobject_rename, gameobject_set_active, and gameobject_set_parent. Sanitization: No sanitization of environment data is specified or required.
Audit Metadata