CVE-2025-48943 | vLLM allows clients to crash the openai server with invalid regex

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.

Published: 2025-05-30 Last update: 2025-06-24 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-48943 is rated Moderate Risk (42.5/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.24%). Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2025-48943

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-03-26 0.07% 0.24% +0.16%
2 2025-11-21 0.20% 0.07% -0.12%
3 2025-11-18 — 0.20% —

Full EPSS history (5 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-48943

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
6.5 3.1 MEDIUM
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.8 3.6 [email protected]

Weakness enumeration for CVE-2025-48943

GitHub Security Advisory for CVE-2025-48943

GHSA-9hcf-v7m4-6m2j · Severity: medium · Ecosystem: pip — vLLM allows clients to crash the openai server with invalid regex

OS Trackers for CVE-2025-48943

vendor priority summary link
redhat medium — https://access.redhat.com/security/cve/CVE-2025-48943

Affected software / configurations for CVE-2025-48943

Vendor Product Version Raw CPE
vllm vllm >= 0.8.0, < 0.9.0 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2025-48943

cvelogic Threat Intelligence