# Triage security vulnerability alerts with NVD and Gemini: n8n workflow

> Started by another system calling it, and works across Jira, Redis and Supabase. It hands the judgement calls to Gemini.

Source: https://millionrounds.com/workflow/triage-security-vulnerability-alerts-with-nvd-and-gemini (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Alerts and monitoring](https://millionrounds.com/workflows?category=Alerts+and+monitoring#library)

# Triage security vulnerability alerts with NVD and Gemini

Started by another system calling it, and works across Jira, Redis and Supabase. It hands the judgement calls to Gemini. 17 steps, 3 branches: a working afternoon to understand properly.

Medium Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftriage-security-vulnerability-alerts-with-nvd-and-gemini)

**17 steps** Medium: a working afternoon

**3** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 5 Model 3 Logic 4 Service 5

The steps in the order they run, from what starts it.

- 1 **When Vulnerability Alert Received** Webhook *Starts it*
- 2 **Gemini Model** Lm Chat Google Gemini *Model*
- 3 **Parse Structured Output** Output Parser Structured *Model*
- 4 **If Valid Payload** If *Logic*
- 5 **Risk Analyst Agent** Agent *Model*
- 6 **Increment Dedup Counter** Redis *Service*
- 7 **Send Invalid Payload Response** Respond To Webhook *Starts it*
- 8 **Route by Risk Level** Switch *Logic*
- 9 **If First Occurrence** If *Logic*
- 10 **Create Remediated Ticket in Jira** Jira *Service*
- 11 **Create Backlog Ticket in Jira** Jira *Service*
- 12 **Fetch NVD Vulnerability Details** Http Request *Service*
- 13 **Send Duplicate Response** Respond To Webhook *Starts it*
- 14 **Send Success Response** Respond To Webhook *Starts it*
- 15 **Send Backlog Response** Respond To Webhook *Starts it*
- 16 **Fetch Server Info from Supabase** Supabase *Service*
- 17 **Prepare LLM Context** Set *Logic*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 17, with 3 branches
- **Size:** Medium: a working afternoon
- **Connects to:** Jira, Redis, Supabase
- **Model:** Gemini

## Questions

What does it need to run?

An n8n account, plus your own Jira, Redis and Supabase accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 17 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 17 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ftriage-security-vulnerability-alerts-with-nvd-and-gemini)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Jira](https://millionrounds.com/workflows?service=Jira#library)[Redis](https://millionrounds.com/workflows?service=Redis#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)

## Workflows like it

Also alerts and monitoring, with the same services where possible, closest in size first.

- [**Classify workflow errors with Claude and Slack** 17 steps · calls a model · Jira, Slack](https://millionrounds.com/workflow/classify-workflow-errors-with-claude-and-slack)
- [**Monitor data quality with Notion and SQL** 17 steps · calls a model · Gmail, Jira](https://millionrounds.com/workflow/monitor-data-quality-with-notion-and-sql)
- [**Aggregate error alerts and send consolidated reports** 17 steps · Email, Jira](https://millionrounds.com/workflow/aggregate-error-alerts-and-send-consolidated-reports)
- [**Error monitor: AI-powered resolution [Context7, Supabase]** 18 steps · calls a model · Email, Supabase](https://millionrounds.com/workflow/error-monitor-ai-powered-resolution-context7-supabase)
- [**Monitor GitHub releases with Gemini and Slack** 18 steps · calls a model · RSS, Redis](https://millionrounds.com/workflow/monitor-github-releases-with-gemini-and-slack)
- [**Company Review Monitor with SendGrid and HubSpot** 16 steps · Email, HubSpot](https://millionrounds.com/workflow/company-review-monitor-with-sendgrid-and-hubspot)