VL
Product
vllm
94
CVEs
0
On KEV
9.8
Max CVSS
11
New 30D
Severity mix
Critical 8High 36Medium 47Low 3
Watch
Add vllm to your stack to get only the CVEs that touch what you run.
| CVE | CVSS | Published | Summary · affected versions |
|---|---|---|---|
| CVE-2026-25960 | 9.8 | Mar 9 | SSRF Protection Bypass in vLLM Affected: 0.15.1 before 0.17.0 |
| CVE-2026-22778 | 9.8 | Feb 2 | vLLM leaks a heap address when PIL throws an error Affected: 0.8.3 before 0.14.1 |
| CVE-2026-22807 | 9.8 | Jan 21 | vLLM is an inference and serving engine for large language models (LLMs) Affected: 0.10.1 before 0.14.0 |
| CVE-2025-47277 | 9.8 | May 20 | vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache… Affected: 0.6.5 before 0.8.5 |
| CVE-2025-32444 | 9.8 | Apr 30 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs Affected: 0.6.5 before 0.8.5 |
| CVE-2024-11041 | 9.8 | Mar 20 | vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function Affected: 0.6.2 |
| CVE-2026-48746 | 9.1 | Jun 22 | vLLM: OpenAI auth bypass Affected: 0.3.0 before 0.22.0 |
| CVE-2025-29783 | 9.0 | Mar 19 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs Affected: 0.6.5 before 0.8.0 |
Showing 8