Vulnerability 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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.6.3, < 0.9.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhpExploitVendor Advisory
- https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-iThird Party Advisory
FAQ
What is CVE-2025-71379?
CVE-2025-71379 is a vulnerability with a CVSS score of 4.3 (MEDIUM). 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 Open...
How severe is CVE-2025-71379?
CVE-2025-71379 has been rated MEDIUM with a CVSS base score of 4.3/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-71379?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.