model-routing

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a logical decision matrix and set of rules for selecting AI models based on the nature of the user's request. This is a best-practice for cost management and system efficiency.
  • [SAFE]: References to model IDs (e.g., claude-haiku-4-5) and pricing are provided for informational and routing purposes. While some model names like claude-fable-5 appear to be placeholders for future or hypothetical versions, they do not trigger dangerous behaviors.
  • [SAFE]: The routing-rules.json file contains structured data for mapping commands and keywords to specific models, which is a standard configuration approach.
  • [SAFE]: No unauthorized network operations, credential harvesting, obfuscation, or command execution patterns were identified in the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 09:38 AM
Security Audit — agent-trust-hub — model-routing