| CVE-2026-44222 |
high |
7.5 |
7.5 |
|
|
|
22d ago |
vLLM Vulnerable to Remote DoS via Special-Token Placeholders |
| CVE-2026-44223 |
medium |
6.5 |
6.5 |
|
|
|
22d ago |
vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect sh… |
| CVE-2026-7141 |
medium |
5.6 |
5.6 |
|
|
|
1mo ago |
vLLM makes Use of Uninitialized Resource |
| CVE-2026-34755 |
unknown |
— |
— |
|
|
|
2mo ago |
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/media/video.py splits video/jpeg data U… |
| CVE-2026-34753 |
unknown |
— |
— |
|
|
|
2mo ago |
vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url ` |
| CVE-2026-34756 |
unknown |
— |
— |
|
|
|
2mo ago |
vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server |
| CVE-2026-27893 |
unknown |
— |
— |
|
|
|
2mo ago |
vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out |
| CVE-2026-25960 |
unknown |
— |
— |
|
|
|
3mo ago |
vLLM has SSRF Protection Bypass |
| CVE-2026-22778 |
unknown |
— |
— |
|
|
|
4mo ago |
vLLM has RCE In Video Processing |
| CVE-2026-24779 |
unknown |
— |
— |
|
|
|
4mo ago |
vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector |
| CVE-2026-22807 |
unknown |
— |
— |
|
|
|
4mo ago |
vLLM affected by RCE via auto_map dynamic module loading during model initialization |
| CVE-2026-22773 |
unknown |
— |
— |
|
|
|
5mo ago |
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 multimodal models that use the Idefics3 visi… |
| CVE-2025-66448 |
unknown |
— |
— |
|
|
|
6mo ago |
vLLM vulnerable to remote code execution via transformers_utils/get_config |
| CVE-2025-62426 |
unknown |
— |
— |
|
|
|
7mo ago |
vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs` |
| CVE-2025-62372 |
unknown |
— |
— |
|
|
|
7mo ago |
vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs |
| CVE-2025-62164 |
unknown |
— |
— |
|
|
|
7mo ago |
vLLM deserialization vulnerability leading to DoS and potential RCE |
| CVE-2025-6242 |
unknown |
— |
— |
|
|
|
8mo ago |
vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class |
| CVE-2025-61620 |
unknown |
— |
— |
|
|
|
8mo ago |
vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server |
| CVE-2025-59425 |
unknown |
— |
— |
|
|
|
8mo ago |
vLLM is vulnerable to timing attack at bearer auth |
| CVE-2025-9141 |
unknown |
— |
— |
|
|
|
10mo ago |
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder |
| CVE-2025-48956 |
unknown |
— |
— |
|
|
|
10mo ago |
vllm API endpoints vulnerable to Denial of Service Attacks |
| CVE-2025-48944 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM Tool Schema allows DoS via Malformed pattern and type Fields |
| CVE-2025-48943 |
unknown |
— |
— |
|
|
|
1y ago |
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 the vLLM server to crash if an invalid r… |
| CVE-2025-48942 |
unknown |
— |
— |
|
|
|
1y ago |
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 invalid json_schema as a Guided Param ki… |
| CVE-2025-46722 |
unknown |
— |
— |
|
|
|
1y ago |
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.py, the MultiModalHasher class has a secu… |
| CVE-2025-46570 |
unknown |
— |
— |
|
|
|
1y ago |
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 mechanism finds a matching prefix chunk, the pre… |
| CVE-2025-48887 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_too… |
| CVE-2025-47277 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service |
| CVE-2025-30165 |
unknown |
— |
— |
|
|
|
1y ago |
Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration |
| CVE-2025-46560 |
unknown |
— |
— |
|
|
|
1y ago |
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service |
| CVE-2025-32444 |
unknown |
— |
— |
|
|
|
1y ago |
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 with mooncake, are vulnerable to remote … |
| CVE-2025-30202 |
unknown |
— |
— |
|
|
|
1y ago |
Data exposure via ZeroMQ on multi-node vLLM deployment |
| CVE-2024-9052 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object |
| CVE-2024-9053 |
unknown |
— |
— |
|
|
|
1y ago |
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints. The core functionality run_server_loop() calls the function _make_handler_coro(), which … |
| CVE-2024-11041 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM Deserialization of Untrusted Data vulnerability |
| CVE-2025-29783 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network inte… |
| CVE-2025-29770 |
unknown |
— |
— |
|
|
|
1y ago |
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 structured output (a.k.a. guided decoding). O… |
| CVE-2025-25183 |
unknown |
— |
— |
|
|
|
1y ago |
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere wit… |
| CVE-2025-24357 |
unknown |
— |
— |
|
|
|
1y ago |
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 is downloaded from huggingface. It uses t… |
| CVE-2024-8939 |
unknown |
— |
— |
|
|
|
2y ago |
vLLM Denial of Service via the best_of parameter |
| CVE-2024-8768 |
unknown |
— |
— |
|
|
|
2y ago |
vLLM denial of service vulnerability |
