CVE-2025-48943 - CVE House

Back to Database

Status published Medium CVE-2025-48943

vLLM allows clients to crash the openai server with invalid regex

6.5 CVSS

Vulnerability 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.

Impact Analysis

Refer to official advisory for detailed impact metrics.

Remediation

Ensure systems are updated to the latest vendor-supplied patch levels.

THREAT MONITOR

Am I Vulnerable?

Launch our assessment wizard to check if your infrastructure is exposed to • CVE-2025-48943

Check My Exposure

Credits & Attribution

No credits recorded in the NVD database.

References

More from vllm-project

View All →

vLLM vulnerable to remote code execution via transformers_utils/get_config

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

VLLM deserialization vulnerability leading to DoS and potential RCE

vLLM vulnerable to timing attack at bearer auth

Affected Vendor

vllm-project

View all reports →

Affected Software

vllm

Vulnerable Versions:

>= 0.8.0, < 0.9.0

Timeline

Official Publish: May 30th, 2025

Last Modified: May 30th, 2025

Added to House: July 22nd, 2026

CVSS Vectors

V3: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Weaknesses (CWE)

MITRE ATT&CK TTPs

T1190 Exploit Public-Facing Application

T1203 Exploitation for Client Execution

T1213 Data from Information Repositories

T1499.003 Application Exhaustion Flood