PatchTheCVECVE-2025-71379: vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabiliti
CVE-2025-71379 is a medium-severity flaw (CVSS 4.3) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
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
Why this priority
- Public exploit reference
A fixed release or distro patch exists.
Risk facts
| CVSS score | 4.3 (Medium) |
| Attack vector | Network (remote) |
| Attack complexity | Low |
| Privileges needed | Low |
| User interaction | None |
| EPSS exploit chance | 0.5% (top 59%) |
| CISA exploited list | No |
| Weakness | CWE-1333 |
| Published | 2026-06-20 |
| Last modified | 2026-10-12 |
Last updated 2026-10-12 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2025-71379?
vllm: upgrade to 0.9.0. Exact commands for each OS are on this page.
Is CVE-2025-71379 being exploited?
CVE-2025-71379 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2025-71379 affect?
CVE-2025-71379 affects vllm. Severity is medium (CVSS 4.3). 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 — ar
How urgent is CVE-2025-71379?
Priority 30/100. Public exploit reference
Software pages
OpenAI and LLM tools vulnerabilities
Related CVEs
- CVE-2026-5497 HIGH 7.5 UPGRADE vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to u
- CVE-2026-48746 CRITICAL 9.1 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54232 HIGH 8.8 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-41523 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54236 MEDIUM 5.3 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)