| CVE-2026-109311 |
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing…
|
7.1
High
|
Oct 12, 2026 |
| CVE-2026-105922 |
A security flaw has been discovered in vllm-project vLLM up to 0.31.0
|
5.3
Medium
|
Oct 6, 2026 |
| CVE-2026-105775 |
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0
|
5.3
Medium
|
Oct 6, 2026 |
| CVE-2026-105760 |
vLLM is an inference and serving engine for large language models
|
5.3
Medium
|
Oct 5, 2026 |
| CVE-2026-105759 |
vLLM is an inference and serving engine for large language models
|
5.9
Medium
|
Oct 5, 2026 |
| CVE-2026-105758 |
vLLM is an inference and serving engine for large language models
|
5.3
Medium
|
Oct 5, 2026 |
| CVE-2026-105757 |
vLLM is an inference and serving engine for large language models
|
6.5
Medium
|
Oct 5, 2026 |
| CVE-2026-105756 |
vLLM is an inference and serving engine for large language models
|
6.5
Medium
|
Oct 5, 2026 |
| CVE-2026-105755 |
vLLM is an inference and serving engine for large language models
|
4.2
Medium
|
Oct 5, 2026 |
| CVE-2026-105754 |
vLLM is an inference and serving engine for large language models
|
6.5
Medium
|
Oct 5, 2026 |
| CVE-2026-105753 |
vLLM is an inference and serving engine for large language models
|
6.5
Medium
|
Oct 5, 2026 |
| CVE-2026-105752 |
vLLM is an inference and serving engine for large language models
|
3.1
Low
|
Oct 5, 2026 |
| CVE-2026-103241 |
A flaw has been found in vllm-project vLLM up to 0.26.0
|
6.9
Medium
|
Sep 30, 2026 |
| CVE-2026-100654 |
vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST…
|
7.1
High
|
Sep 26, 2026 |
| CVE-2026-100653 |
vLLM is an inference and serving engine for large language models
|
8.3
High
|
Sep 26, 2026 |
| CVE-2026-100651 |
vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint…
|
7.1
High
|
Sep 26, 2026 |
| CVE-2026-100652 |
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC…
|
8.2
High
|
Sep 26, 2026 |
| CVE-2026-100650 |
vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls…
|
7.1
High
|
Sep 26, 2026 |
| CVE-2026-100649 |
vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler…
|
6.3
Medium
|
Sep 26, 2026 |
| CVE-2026-100647 |
vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on…
|
6.9
Medium
|
Sep 26, 2026 |
| CVE-2026-100648 |
vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing…
|
6.9
Medium
|
Sep 26, 2026 |
| CVE-2026-94627 |
vLLM Mooncake connector through 0.29.0 fails to properly manage GPU KV cache block ownership when concurrent child…
|
8.7
High
|
Sep 21, 2026 |
| CVE-2026-94626 |
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion…
|
8.7
High
|
Sep 21, 2026 |
| CVE-2026-94625 |
vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests…
|
6.9
Medium
|
Sep 21, 2026 |
| CVE-2026-94624 |
vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is…
|
8.7
High
|
Sep 21, 2026 |