create-flow

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • Use of Managed Tools: The skill interacts with the environment through a predefined set of MCP (Model Context Protocol) tools specifically designed for flow management. These tools are scoped to the intended functionality of the skill.
  • User Confirmation Checkpoints: The instructions explicitly require the agent to present the design to the user and obtain confirmation via the AskUserQuestion tool before proceeding to create or publish a flow, which helps prevent unintended actions.
  • Validation Steps: The skill incorporates mandatory validation and preflight checks using validate_flow and preflight_flow to ensure the integrity of the generated definitions before deployment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:56 AM
Security Audit — agent-trust-hub — create-flow