AkihiroSuda/vexllm

silence negligible CVE alerts using LLM

45
/ 100
Emerging

This project helps security and DevOps engineers manage the flood of vulnerability alerts. It takes a JSON report from a vulnerability scanner like Trivy, processes it with an AI, and outputs a refined report in formats like `.trivyignore` or OpenVEX. This allows teams to automatically filter out "negligible" alerts, focusing only on real threats relevant to their specific application or environment.

Use this if you are overwhelmed by false positive or low-priority CVE alerts from your vulnerability scanner and want an AI to help intelligently silence them.

Not ideal if you prefer to manually review and justify every single vulnerability alert without AI assistance, or if you don't use Trivy or a similar scanner.

vulnerability-management DevOps security-operations alert-fatigue risk-prioritization
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

65

Forks

7

Language

Go

License

Apache-2.0

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/AkihiroSuda/vexllm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.