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.
Fix
Patch, vendor advisory and mitigation references on NVD 1
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp Exploit, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 5.3 · vllmNVD modified 2026-10-12 22:10
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 2
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp Exploit, Vendor Advisory
- https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components Third Party Advisory