foundation-models-on-device
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of documentation and Swift code snippets designed to guide developers in using Apple's on-device AI framework. No malicious instructions, data exfiltration patterns, or security bypasses were identified.
- [NO_CODE]: The skill does not include any executable scripts, shell commands, or external dependencies. It is limited to informational markdown content.
- [SAFE]: No obfuscation, base64-encoded strings, or hidden URLs were found within the skill content. All code examples are standard Swift implementations for local model interaction.
Audit Metadata