axiom-ios-vision

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as a structural router for AI agents. It contains no executable scripts, shell commands, or network operations.
  • [SAFE]: All instructions are restricted to internal routing logic ($axiom-vision, $axiom-vision-ref, etc.) and provide standard developer guidance for the Apple Vision framework.
  • [SAFE]: No data exposure or prompt injection risks were detected. The skill's primary function is to direct the agent to specific sub-skills based on user intent related to computer vision tasks like OCR, pose detection, and document scanning.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:54 AM