The VLAI Severity model is accessible via API. Here is a simple example from a recent Ivanti vulnerability description from their vulnerability webpage.
The VLAI Security model for vulnerabilities is accessible via vulnerability-lookup and the public instance operated by CIRCL.
So, if you have a vulnerability description, you can quickly assess it to get a general idea of its severity.
curl -X 'POST' \
'https://vulnerability.circl.lu/api/vlai/severity-classification' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{ "description": "Ivanti has released updates for Ivanti Neurons for ITSM (on-prem only) which addresses one critical severity vulnerability. Depending on system configuration, successful exploitation could allow an unauthenticated remote attacker to gain administrative access to the system. We are not aware of any customers being exploited by these vulnerabilities at the time of disclosure. We have included an environmental score to provide customers with additional context on the adjusted risk of this vulnerability with typical use cases. Customers who have followed Ivanti guidance on securing the IIS website and restricted access to a limited number of IP addresses and domain names have a reduced risk to their environment. Customers who have users log into the solution from outside their company network also have a reduced risk to their environment if they ensure that the solution is configured with a DMZ." }'
and the result
{
"severity": "Critical",
"confidence": 0.9256
}
#cve #ivanti #vulnerability #vulnerabilitymanagement #vulnerabilities
For more details: https://www.vulnerability-lookup.org/2025/05/22/vulnerability-lookup-2-10-0/#ai-powered-enrichment-using-our-in-house-ai-models
@circl @gcve