What is the CVSS score of CVE-2025-48942?

CVE-2025-48942 has a CVSS 3.1 base score of 6.5 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H. EPSS exploitation probability: 0.2%.

Which versions of Vllm are affected by CVE-2025-48942?

Organizations using versions 0.8.0 should be aware of notable risk from CVE-2025-48942 rated CVSS 6.5. Exploitation could compromise the security of affected deployments.. A patch is available.

Is there a public PoC exploit available for CVE-2025-48942?

Yes, a public proof-of-concept exploit is available for CVE-2025-48942. Prioritise patching immediately. EPSS: 0.2%.

How to fix or mitigate CVE-2025-48942?

Within 7 days: Identify affected systems running versions 0.8.0 and apply vendor patches promptly. Vendor patch is available.

Vllm CVE-2025-48942

MEDIUM

Uncaught Exception (CWE-248)

2025-05-30 security-advisories@github.com

Information Disclosure Red Hat Vllm

6.5

CVSS 3.1

CVSS VectorNVD

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 18:44 vuln.today

Patch released

Mar 28, 2026 - 18:44 nvd

Patch available

PoC Detected

Jun 24, 2025 - 17:44 vuln.today

Public exploit code

CVE Published

May 30, 2025 - 19:15 nvd

MEDIUM 6.5

DescriptionNVD

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.

AnalysisAI

vLLM is an inference and serving engine for large language models (LLMs). Rated medium severity (CVSS 6.5), this vulnerability is remotely exploitable, low attack complexity. Public exploit code available.

Technical ContextAI

This vulnerability is classified under CWE-248. 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 products include: Vllm. Version information: Version 0.9.0.

RemediationAI

A vendor patch is available. Apply the latest security update as soon as possible. Apply vendor patches when available. Implement network segmentation and monitoring as interim mitigations.