omni-ai-optimizer

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the vendor's official command-line interface tool (omni) to interact with models. All commands, such as omni models yaml-create and omni models create-branch, are standard administrative operations for the platform.
  • [SAFE]: External references are restricted to well-known vendor resources, including the official GitHub repository (exploreomni/cli) and technical documentation (docs.omni.co).
  • [SAFE]: The skill implements a 'Branch first' policy, ensuring that the AI does not modify production model YAML directly without user confirmation, which mitigates the risk of accidental or malicious configuration changes.
  • [SAFE]: Sensitive authentication processes (OAuth/API keys) are handled externally by the user via the omni config login command, ensuring that credentials are not handled or stored by the agent itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 12:58 PM