CVE-2025-59425highCWE-385

CVE-2025-59425: high-severity vulnerability in vllm-project vllm

vLLM vulnerable to timing attack at bearer auth

Published

21Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 7.5epss 0.6%
exploitation probability
0.6%top 55% of all CVEs
observed exploitation
nono source reports it
In short

vLLM's API key validation is vulnerable to timing attacks, where an attacker can guess the correct API key character-by-character by measuring how long the server takes to reject each attempt. This allows attackers to bypass authentication and gain unauthorized access to the LLM service.

Technical detail

The API key validation in vLLM uses string comparison that exhibits timing variation based on the number of correct characters matched, enabling a timing side-channel attack. An attacker can iteratively determine each character of the API key by analyzing response times across multiple authentication attempts, leading to authentication bypass and unauthorized API access.

Summary generated and translated by AI from the official 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:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Affected products
vllm-project · vllm
Related CVEs — vllm-project vllm

In the same product, most dangerous first.

CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 11.2%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.8%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%CVE-2025-62164HIGHVLLM deserialization vulnerability leading to DoS and potential RCEEPSS 0.9%
References
https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48https://github.com/vllm-project/vllm/releases/tag/v0.11.0https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm