Description
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.
References (4)
Scores
CVSS v3
6.5
EPSS
0.0024
EPSS Percentile
46.7%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CISA SSVC
Vulnrichment
Exploitation
none
Automatable
no
Technical Impact
partial
Details
CWE
CWE-248
Status
published
Products (2)
pypi/vllm
0.8.0 - 0.9.0PyPI
vllm/vllm
0.8.0 - 0.9.0
Published
May 30, 2025
Tracked Since
Feb 18, 2026