analyze_workflow
Retrieve detailed analysis of a single workflow: member nodes, inference signals, top-5 risk nodes with breakdown, and adversarial probes. Use after list_workflows to examine the highest-risk workflow.
Instructions
Deep-dive on a single workflow by id: returns every member node, every inference signal that placed it in this workflow (path token / import token / symbol token + weight), the top-5 highest-risk nodes with full risk breakdown, all runtime-risk hypotheses, and the adversarial probe deck. Use this after list_workflows surfaces the one you care about — typically the highest-max-risk workflow affected by a PR.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| workflowId | Yes | Workflow identifier from list_workflows (e.g., 'payments', 'authentication', 'webhooks'). |
Implementation Reference
- src/models/WorkflowModels.ts:41-48 (helper)The WorkflowDomain interface representing the return type for a single workflow's domain data (id, name, kind, members, signals, confidence).
export interface WorkflowDomain { id: string; // stable slug (e.g. "authentication") name: string; // pretty label kind: WorkflowKind; memberNodeIds: string[]; signals: WorkflowSignal[]; // why we clustered these confidence: number; // 0..100 — strength of inference }