axiom-ios-ml-coreml-diag
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a legitimate technical reference for troubleshooting CoreML performance, memory, and conversion issues using standard Apple development workflows.
- [EXTERNAL_DOWNLOADS]: The skill mentions
pip install --upgrade coremltools. This refers to the official library maintained by Apple for CoreML model conversion and optimization. As this is a well-known resource from a trusted vendor essential to the skill's primary purpose, it does not represent a security risk. - [COMMAND_EXECUTION]: Code snippets include the use of
ls -lhto verify model package weights on the filesystem. This is a standard and safe practice for diagnosing model size and storage issues. - [INDIRECT_PROMPT_INJECTION]: The skill describes processes for ingesting and analyzing model metadata and performance reports.
- Ingestion points: CoreML model packages (
.mlpackage) and Xcode Performance Reports. - Boundary markers: None identified in the instructional text.
- Capability inventory: Local file metadata inspection and model specification reading via Python.
- Sanitization: Standard diagnostic use case; no specific sanitization mentioned for log analysis.
Audit Metadata