---
id: GHSA-vfm7-4h43-gp6m
title: 'Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service'
summary: 'Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service'
severity: medium
cvss: 4.3
cwe:
  - CWE-1333
vendor: vllm
product: vllm
ecosystem: pip
affected:
  - 'vllm >= 0.6.3, < 0.9.0'
patched:
  - vllm 0.9.0
published: '2026-06-20'
updated: '2026-09-11'
sourceUpdated: '2026-09-11T15:45:35Z'
source: GHSA
sourceUrl: 'https://github.com/advisories/GHSA-vfm7-4h43-gp6m'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2025-71379'
  - url: >-
      https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components
  - url: 'https://github.com/advisories/GHSA-vfm7-4h43-gp6m'
tags:
  - ghsa
  - pip
ingestedAt: '2026-09-11T16:45:47.862Z'
---

## Overview

### Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references.

### Original Description

vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.

## Affected packages

- `vllm >= 0.6.3, < 0.9.0`

## Remediation

Upgrade to a patched release:

- `vllm 0.9.0`