Skip to main content
← All vulnerabilities
CVE-2025-71379GHSA-J828-28RJ-HFHP

vllm - Regular Expression Denial of Service in Multiple Components

Published
Last modified
published
Not listed in CISA KEV
Fix
Fixed in 0.9.0
None on Exploit-DB, Metasploit or GitHub
  • Exploitation: none
  • Automatable: no
  • Technical impact: partial

Summary

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.

Timeline

  1. CVE published
  2. CISA SSVC assessment

    Exploitation: none · Automatable: no · Technical impact: partial

  3. Record last updated

Affected versions

  • vllm vllm

    From 0.6.3 · fixed in 0.9.0

  • vllmPyPI

    From 0.6.3 · fixed in 0.9.0

References 2

GitHub · vllm-project/vllm

vulncheck.com