CVE-2025-59425 - Vulnerability Details

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.

No CVSS v4.0

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact High

Integrity Impact None

Availability Impact None

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

The EPSS score is 0.00291.

Exploitation none

Automatable yes

Technical Impact partial

Vendors	Products
Vllm	Vllm
Vllm-project	Vllm

Configuration 1 [-]

OR	cpe:2.3:a:vllm:vllm::::::::
	cpe:2.3:a:vllm:vllm:0.11.0:rc1::::::

No data.

OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.

Vendors	Products
Vllm-project	Vllm

Advisories

Source	ID	Title
Github GHSA	GHSA-wr9h-g72x-mwhm	vLLM is vulnerable to timing attack at bearer auth

Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References

Link	Providers
https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274
https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48
https://github.com/vllm-project/vllm/releases/tag/v0.11.0
https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm
https://nvd.nist.gov/vuln/detail/CVE-2025-59425
https://www.cve.org/CVERecord?id=CVE-2025-59425

History

Thu, 16 Oct 2025 18:15:00 +0000

Type	Values Removed	Values Added
First Time appeared		Vllm Vllm vllm
CPEs		cpe:2.3:a:vllm:vllm:::::::: cpe:2.3:a:vllm:vllm:0.11.0:rc1::::::
Vendors & Products		Vllm Vllm vllm

Wed, 08 Oct 2025 13:45:00 +0000

Type	Values Removed	Values Added
First Time appeared		Vllm-project Vllm-project vllm
Vendors & Products		Vllm-project Vllm-project vllm

Tue, 07 Oct 2025 16:15:00 +0000

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}`

Tue, 07 Oct 2025 14:15:00 +0000

Type	Values Removed	Values Added
Description	A flaw was found in vLLM’s API token authentication logic, where token comparisons were not performed in constant time. This weakness could allow an attacker to exploit timing differences to guess valid tokens and bypass authentication.	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.
Title	vllm: Timing Attack in vLLM API Token Verification Leading to Authentication Bypass	vLLM vulnerable to timing attack at bearer auth
Weaknesses		CWE-385
References		https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274 https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48 https://github.com/vllm-project/vllm/releases/tag/v0.11.0 https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm

Tue, 07 Oct 2025 12:15:00 +0000

Type	Values Removed	Values Added
Description		A flaw was found in vLLM’s API token authentication logic, where token comparisons were not performed in constant time. This weakness could allow an attacker to exploit timing differences to guess valid tokens and bypass authentication.
Title		vllm: Timing Attack in vLLM API Token Verification Leading to Authentication Bypass
Weaknesses		CWE-208
References		https://nvd.nist.gov/vuln/detail/CVE-2025-59425 https://www.cve.org/CVERecord?id=CVE-2025-59425
Metrics	threat_severity `None`	cvssV3_1 `{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N'}` threat_severity `Important`

MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published: 2025-10-07T14:06:49.042Z

Updated: 2025-10-07T15:28:10.303Z

Reserved: 2025-09-15T19:13:16.905Z

Link: CVE-2025-59425

Vulnrichment

Updated: 2025-10-07T14:32:28.595Z

NVD

Status : Analyzed

Published: 2025-10-07T14:15:38.950

Modified: 2025-10-16T18:02:09.260

Link: CVE-2025-59425

Redhat

Severity : Important

Publid Date: 2025-10-07T00:00:00Z

Links: CVE-2025-59425 - Bugzilla

OpenCVE Enrichment

Updated: 2025-10-08T13:36:42Z

Metrics

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact High

Integrity Impact None

Availability Impact None

User Interaction None

Exploitation none

Automatable yes

Technical Impact partial

Affected Vendors & Products

JSON object

JSON object

JSON object

JSON object

JSON object