Remediate critical attack paths with Neo4j, OpenAI, GitHub and Jira
Needs changesWhat this workflow does
This AI workflow has 18 nodes and runs on a schedule (cron 0 5 * * *) (plus 1 other trigger). Along the way it connects OpenAI Chat Model.
How it runs
Trigger: On a schedule (cron 0 5 * * *) (plus 1 other trigger).
- Set Configuration Parameters (Edit Fields (Set)): sets 9 fields: neo4jUrl, riskScoreThreshold, jiraBaseUrl…
- Post to Security Graph API (HTTP Request): calls an HTTP API (POST)
- Parse and Extract Attack Paths (Code): runs custom JavaScript code
- Wait: pauses before continuing
- Analyze and Rank Attack Paths (Code): runs custom Python code
- If: checks a condition and branches into true / false
- Retrieve IaC File from GitHub (HTTP Request): calls an HTTP API
- Remediation Strategy Agent (AI Agent): runs an AI agent, with model: OpenAI GPT-4.1 Mini Agent
- Parse AI and Build Payloads (Code): runs custom JavaScript code
- Submit Jira Issue API (HTTP Request): calls an HTTP API (POST)
…plus 5 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Remediation Strategy Agent (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Remediation Strategy Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Wait
n8n-nodes-base.wait
From the author
Quick overview This workflow scans a Neo4j-compatible security graph on a schedule or manually, automatically identifies and remediates the riskiest attack paths between internet-facing assets and crown-jewel resources using OpenAI, and orchestrates…