unity-animator
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data through Unity-specific parameters which could serve as a vector for indirect prompt injection.
- Ingestion points: The skill accepts input from the Unity environment and user-supplied strings for parameters such as
controllerPath,name,path, andstateNameacross various skills inSKILL.md. - Boundary markers: No explicit delimiters or instruction-isolation warnings are implemented for the string parameters processed by the AI.
- Capability inventory: The skill allows creating new controller assets (
animator_create_controller), modifying existing state machines (animator_add_state,animator_add_transition), and altering runtime behavior (animator_set_parameter). - Sanitization: There is no evidence of string sanitization or validation for the asset paths or identifiers before they are incorporated into the agent's context or passed to the underlying Unity bridge.
Audit Metadata