# CVE-2025-59425

## Summary

- **CVE ID:** CVE-2025-59425
- **Severity:** HIGH
- **CVSS Score:** 7.5 (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N)
- **CWE:** CWE-385
- **Published:** Oct 7, 2025
- **Last Modified:** Mar 13, 2026

## 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.

## Affected Products

- vllm-project — vllm (< 0.11.0rc2)

## References

- [CNA](https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm)
- [CNA](https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48)
- [CNA](https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274)
- [CNA](https://github.com/vllm-project/vllm/releases/tag/v0.11.0)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.57%
- **EPSS Percentile:** 45.1

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._