CVE-2025-48943CWE-248

vLLM allows clients to crash the openai server with invalid regex

Medium · published May 30, 2025

CVSS v3.1
6.5
EPSS
0%
Percentile
41.0
In the wild
Unconfirmed
What it is

vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

The record
Technical detail
CVSS v3.1
6.5 · MEDIUM
Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS v4.0
Not supplied
EPSS
0.00487 · 41.0th percentile
Weakness
CWE-248 · Uncaught Exception
Published
2025-05-30T18:36Z
EPSS history
Timeline
  • 30 MAY 18:36Z
    vLLM allows clients to crash the openai server with invalid regex
    cvelistv5