CVE-2025-48943
vLLM allows clients to crash the openai server with invalid regex
6.5
MEDIUM
CVSS 3.1
EPSS 0.24%
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.
How to fix CVE-2025-48943
To remediate CVE-2025-48943, upgrade the affected package to a fixed version below.
- —upgrade to 0.9.0 or later
- —upgrade to 08bf7840780980c7568c573c70a6a8db94fd45ff or later
Is CVE-2025-48943 being exploited?
Low — EPSS is 0.2%, meaning exploitation activity has not been observed at scale.
Affected packages (2)
- >= 0.8.0, < 0.9.0
- from 0, < 08bf7840780980c7568c573c70a6a8db94fd45ff | >= 0.8.0, < 0.9.0
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | MEDIUM6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |