axiom-ios-ml-coreml-ref
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation reference for developers. All provided Swift and Python code snippets are standard implementation examples for machine learning tasks such as model loading, inference, and quantization.
- [EXTERNAL_DOWNLOADS]: The Python examples reference well-known machine learning libraries (coremltools, torch) which are standard for the described use case.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, such as piping shell scripts from the web, were detected.
- [DATA_EXFILTRATION]: There are no network operations or sensitive file access patterns that would indicate data exfiltration.
- [PROMPT_INJECTION]: The instructions do not contain any attempts to bypass safety filters or override agent behavior instructions.
Audit Metadata