models

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is the management of local configuration files (.claude/omc.jsonc and claude-omc/config.jsonc) to define model routing for different agent roles. This is a standard utility function for development tools.
  • [SAFE]: External references in the metadata point to reputable repositories on GitHub (Cursor's official plugins and a community port), which are used for attribution and documentation. These references do not pose a security risk as they target well-known and legitimate project sources.
  • [SAFE]: The skill includes instructions to confirm changes with the user before writing and validates configuration values against allowed providers and tiers, which helps prevent accidental or malicious misconfiguration.
  • [SAFE]: The skill identifies and interacts with standard, non-sensitive configuration paths based on environment variables such as $XDG_CONFIG_HOME and %APPDATA%, following platform best practices for configuration management.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 07:21 PM