Vulnerability · Published May 30, 2025 · Assigned by GitHub_M

CVE-2025-48942vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Medium 6.5

In plain English

A medium-severity security flaw in vllm from vllm-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 48% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium
Exploit odds (30 days)0.6%top 52.4% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIvllm0.9.0GHSA-6qc9-v4r8-22xg
PyPIvllm0.9.0PYSEC-2025-54

Affected products (as reported)

VendorProductVersions
vllm-project vllm >= 0.8.0, < 0.9.0

Weakness: CWE-248 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References