GitHub Advisoryadvisory · PyPI

GHSA-wr9h-g72x-mwhm vLLM is vulnerable to timing attack at bearer auth

HIGH Published 2025-10-07 Modified 2026-07-17 Official page ↗
Aliases
CVE-2025-59425
Ecosystem
PyPI
Packages
vllm
Severity
High
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Weaknesses
CWE-385
Reviewed
2025-10-07

Affected packages

• PyPI vllm: < 0.11.0 → fixed in 0.11.0

Description

Summary The API key support in vLLM performed validation using a method that was vulnerable to a timing attack. This could potentially allow an attacker to discover a valid API key using an approach more efficient than brute force. Details https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274 API key validation used a string comparison that will take longer the more characters the provided API key gets correct. Data analysis across many attempts can allow an attacker to determine when it finds the next correct character in the key sequence. Impact Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique.

Related

Alias · CVE (1)

  • CVE-2025-59425 vLLM is an inference and serving engine for large language models (LLMs). vulnerability

Weakness · CWE (1)

  • CWE-385 Covert Timing Channel weakness

References