6.5

CVE-2025-48942: vllm-project vllm Uncaught Exception

CVSS: 6.5v3.1MediumAnalyzed
AliasesGHSA-6qc9-v4r8-22xgPYSEC-2025-54
Published 30-05-2025Last modified 30-05-2025

Vulnerability summary

CVE-2025-48942 is a medium (CVSS 6.5) Uncaught Exception vulnerability in vllm-project vllm. EPSS estimates a 0.55% chance of exploitation in the next 30 days, higher than 45% of scored vulnerabilities. 1 public exploit is recorded.

Overall risk
36/100
0100
Medium · default modelHow is this calculated?
CVSS score
6.5/10
010
Medium · v3.1 (CVE.org)
EPSS score
0.55%
0%100%
Low · +0.01 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits1github

Advisory lineage

Upstream 0 · Downstream 0 · Related 2

Timeline

  1. 30-05-2025
    PublishedVulnerability first disclosed.
  2. 30-05-2025
    Last modifiedVulnerability information updated.

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.

CVSS metrics

3 scores · 3 sources · 1 version

EPSS trend

Probability

0.55%

Chance of exploitation in the next 30 days

Percentile

45%

Versus all other CVEs

30-day change

+0.01 pp

From 0.54% on 20-09-2026

20-09-202620-10-2026
EPSS score
0.55%

Known exploited

Compare KEV catalogs

Not in any of the 3 tracked catalogs.

Public exploits

1 found
  • githubUnverified

    Vllm

    Maturity: poc

Weaknesses

CWE · root cause

Affected systems

PyPI1 product
  • vllm< 08bf7840780980c7568c573c70a6a8db94fd45ff | ≥ 0.8.0, < 0.9.0
Vllm1 product
  • vllm≥ 0.8.0, < 0.9.0
Vllm-project1 product
  • vllm≥ 0.8.0, < 0.9.0

3 vendors · 3 products

References

7 links