Introducing openrisk, our first AI-powered tool

Introducing openrisk, our first AI-powered tool
DALL-E, openrisk logo, 2022

Today, we are excited to announce the openrisk, a new way to risk score creation powered by OpenAI GPT-3. This new tool creates a simple risk score for a single host by reading its nuclei scan output.

Fun fact: Some of the code in openrisk is written by OpenAI GPT-3.

What is risk score?

A risk score is a numerical value representing the risk associated with a particular host. It helps security professionals prioritize their efforts in addressing vulnerabilities on a host, with higher risk scores indicating a greater need for immediate attention.


If you're a security professional, you know the importance of regularly scanning your systems for vulnerabilities. It's a crucial part of any security plan, as it helps identify and mitigate potential risks before attackers can exploit them. But with so many different hosts to keep track of, it can be difficult to prioritize and decide where to start first. That's where openrisk comes in.


By using openrisk, you can quickly and easily create a risk for the host you scanned with nuclei. This allows you to prioritize efforts and focus on mitigating the most critical hosts first.

Try Now

If you're interested in giving openrisk a try, head to the openrisk's GitHub repository to learn more and get started. With its AI-powered risk scoring, openrisk is a valuable addition to any security professional's toolkit for nuclei.

Note: This is an experimental program released by the ProjectDiscovery Research Team. As such, it may not meet the same code quality standards as our other projects, and may not be as well-tested. We welcome suggestions, bug fixes, and ideas on integrating these experiments into our other tools!

Subscribe to our newsletter and stay updated.

Don't miss anything. Get all the latest posts delivered straight to your inbox. It's free!
Great! Check your inbox and click the link to confirm your subscription.
Error! Please enter a valid email address!
--