foundation-models-on-device
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for developers, providing Swift code snippets for text generation, tool calling, and structured output using a fictional on-device framework.
- [SAFE]: No evidence of malicious prompt injection, data exfiltration, or obfuscation was found within the instructions or code examples.
- [SAFE]: The skill explicitly promotes security and privacy best practices, such as performing availability checks and using instructions to define safety guardrails for model responses.
Audit Metadata