CVE-2025-48943
MEDIUMvLLM 0.8.0-0.8.9 - Denial of Service via Invalid Regex in Structured Output
Title source: llmDescription
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)
Core 4
Core References
Vendor Advisory x_refsource_confirm
https://github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j
Issue Tracking x_refsource_misc
https://github.com/vllm-project/vllm/issues/17313
Issue Tracking, Patch x_refsource_misc
https://github.com/vllm-project/vllm/pull/17623
Scores
CVSS v3
6.5
EPSS
0.0039
EPSS Percentile
30.7%
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