Vllm-Project
Page 2 of 2 — Vllm-Project CVEs from a corpus of 132, newest first, with CVSS severity and publication dates.
| CVE | Severity | Score | Published | Summary |
|---|---|---|---|---|
CVE-2026-34755 | Medium | 6.5 | 2026-04-06 | vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal… |
CVE-2026-34753 | Medium | 5.4 | 2026-04-06 | vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in d… |
CVE-2026-34760 | Medium | 5.9 | 2026-04-02 | vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for… |
CVE-2026-27893 | High | 8.8 | 2026-03-27 | vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation file… |
CVE-2026-25960 | High | 7.1 | 2026-03-09 | vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_… |
CVE-2026-22778 | Critical | 9.8 | 2026-02-02 | vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpo… |
CVE-2026-24779 | High | 7.1 | 2026-01-27 | vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.14.1, a Server-Side Request Forgery (SSRF) vulnerability exists in… |
CVE-2026-22807 | High | 8.8 | 2026-01-21 | vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto… |
CVE-2026-22773 | Medium | 6.5 | 2026-01-10 | vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving mult… |
CVE-2025-66448 | High | 7.1 | 2025-12-01 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class n… |
CVE-2025-62426 | Medium | 6.5 | 2025-11-21 | vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints… |
CVE-2025-62372 | Medium | 6.5 | 2025-11-21 | vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimod… |
CVE-2025-62164 | High | 8.8 | 2025-11-21 | vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead t… |
CVE-2025-59425 | High | 7.5 | 2025-10-07 | vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a met… |
CVE-2025-48956 | High | 7.5 | 2025-08-21 | vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be trigger… |
CVE-2025-48944 | Medium | 6.5 | 2025-05-30 | vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/c… |
CVE-2025-48943 | Medium | 6.5 | 2025-05-30 | vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes… |
CVE-2025-48942 | Medium | 6.5 | 2025-05-30 | vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a… |
CVE-2025-48887 | Medium | 6.5 | 2025-05-30 | vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entr… |
CVE-2025-46722 | Medium | 4.2 | 2025-05-29 | vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.p… |
CVE-2025-46570 | Low | 2.6 | 2025-05-29 | vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanis… |
CVE-2025-47277 | Critical | 9.8 | 2025-05-20 | 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 `… |
CVE-2025-30165 | High | 8.0 | 2025-05-06 | vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node co… |
CVE-2025-46560 | Medium | 6.5 | 2025-04-30 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critica… |
CVE-2025-32444 | Critical | 10.0 | 2025-04-30 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration… |
CVE-2025-30202 | High | 7.5 | 2025-04-30 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial… |
CVE-2024-9053 | Critical | 9.8 | 2025-03-20 | vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints. The core functionality run_server_loop() calls t… |
CVE-2024-11041 | Critical | 9.8 | 2025-03-20 | vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets… |
CVE-2025-29783 | Critical | 9.0 | 2025-03-19 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed d… |
CVE-2025-29770 | Medium | 6.5 | 2025-03-19 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support struc… |
CVE-2025-25183 | Low | 2.6 | 2025-02-07 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting… |
CVE-2025-24357 | High | 7.5 | 2025-01-27 | vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which i… |