7.5

CVE-2025-59425: vllm-project vllm Covert Timing Channel

CVSS: 7.5v3.1HighAnalyzed
AliasesGHSA-wr9h-g72x-mwhmPYSEC-2026-2026CGA-4g9w-x437-9rpq
Published 07-10-2025Last modified 07-10-2025

Vulnerability summary

CVE-2025-59425 is a high (CVSS 7.5) Covert Timing Channel vulnerability in vllm-project vllm. EPSS estimates a 0.57% chance of exploitation in the next 30 days, higher than 45.9% of scored vulnerabilities. 1 public exploit is recorded.

Overall risk
40/100
0100
Medium · default modelHow is this calculated?
CVSS score
7.5/10
010
High · v3.1 (CVE.org)
EPSS score
0.57%
0%100%
Low · 0.00 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits1github

Advisory lineage

Upstream 0 · Downstream 0 · Related 3

Timeline

  1. 07-10-2025
    PublishedVulnerability first disclosed.
  2. 07-10-2025
    Last modifiedVulnerability information updated.

Description

vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue.

CVSS metrics

4 scores · 4 sources · 1 version

EPSS trend

Probability

0.57%

Chance of exploitation in the next 30 days

Percentile

46%

Versus all other CVEs

30-day change

0.00 pp

From 0.57% on 20-09-2026

20-09-202620-10-2026
EPSS score
0.57%

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

Chainguard5 products
  • py3-vllm-cuda-12.4< 0.11.0-r2
  • py3.10-vllm-cuda-12.4< 0.11.0-r2
  • py3.12-vllm-cuda-12.4< 0.11.0-r2
  • tritonserver-backend-vllm-cuda-12.9< 25.9.0_git20251016-r0
  • tritonserver-backend-vllm-meta-cuda-12.9< 25.9.0_git20251016-r0
PyPI1 product
  • vllm< 0.11.0
Vllm1 product
  • vllm< 0.11.0 | 0.11.0:rc1
Vllm-project1 product

4 vendors · 8 products

References

10 links