CVE-2025-71379

medium

Description

vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.

References

https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components

https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp

Details

Source: Mitre, NVD

Published: 2026-06-20

Updated: 2026-06-22

Risk Information

CVSS v2

Base Score: 4

Vector: CVSS2#AV:N/AC:L/Au:S/C:N/I:N/A:P

Severity: Medium

CVSS v3

Base Score: 4.3

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L

Severity: Medium

CVSS v4

Base Score: 5.3

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

Severity: Medium