CVE-2025-48942

vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the  /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTNIST
6.5 MEDIUM
NETWORK
LOW
LOW
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
GitHub_MCNA
6.5 MEDIUM
NETWORK
LOW
LOW
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CISA-ADPADP
---
---
Base Score
CVSS 3.x
EPSS Score
Percentile: 16%
VendorProductVersion
vllmvllm
0.8.0 ≤
𝑥
< 0.9.0
𝑥
= Vulnerable software versions
Common Weakness Enumeration
References
https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff
https://github.com/vllm-project/vllm/issues/17248
https://github.com/vllm-project/vllm/pull/17623
https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg