apple-on-device-ai
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate technical documentation for Apple's Foundation Models, Core ML, and MLX frameworks. All provided code snippets are standard developer implementations for model conversion, optimization, and inference.\n- [EXTERNAL_DOWNLOADS]: The skill references standard machine learning development tools, such as the
coremltoolsPython package and the Hugging Face model registry. These are official or well-known resources in the ML ecosystem and do not represent a security risk.\n- [INDIRECT_PROMPT_INJECTION]: The documentation identifies the attack surface for indirect prompt injection when processing user-provided content. It provides proactive security advice, such as separating user input from system instructions and relying on the mandatory, platform-enforced guardrails of Apple's Foundation Models.
Audit Metadata