realitykit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and code samples follow official RealityKit and ARKit best practices, including mandatory privacy declarations (NSCameraUsageDescription) and runtime capability checks (ARWorldTrackingConfiguration.isSupported).
- [SAFE]: Evaluation scenarios in evals.json are designed to test the agent's ability to identify and correct poor security practices, such as missing camera permissions and lack of hardware support validation.
- [SAFE]: External references point to documentation sites for RealityKit and ARKit; while some use the non-standard domain sosumi.ai, the content provided within the skill itself is technically accurate and centered on standard Apple frameworks.
Audit Metadata