axiom-ai
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical resource for developers working with Apple Intelligence and CoreML. It provides safe coding patterns and architectural advice.
- [PROMPT_INJECTION]: The skill includes explicit security warnings and design patterns to mitigate prompt injection. It instructs developers to never interpolate untrusted user input into model instructions and to use dedicated prompt parameters instead.
- [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. The skill focuses on on-device AI processing which inherently prioritizes privacy.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or install unverifiable dependencies. All references to external tools (like the 'claude-api' skill) are informational or routing-based.
- [COMMAND_EXECUTION]: No dangerous shell commands or arbitrary code execution patterns were found. The code snippets provided are for standard Swift application development.
Audit Metadata