| Component | vLLM |
| Severity | medium (CVSS 4.3) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L |
| Published (NVD) | 2026-10-06 |
| Last modified | 2026-10-09 |
| Affected versions | vllm <= 0.31.0 |
| Fixed in | see the vendor advisory |
| Weakness | CWE-404 |
| CISA KEV | not listed |
NVD description
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file vllm/model_executor/layers/utils.py of the component Penalty Handler. Performing a manipulation results in denial of service. Remote exploitation of the attack is possible. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep vLLM off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-105922
- https://gist.github.com/Yunzez/5c70a3bb328eaf6d646b9d31e879dc4a#file-repro_prompt_embeds_penalties_engine_crash-py
- https://vuldb.com/cve/CVE-2026-105922
- https://vuldb.com/submit/992707
- https://vuldb.com/vuln/413896
- https://github.com/vllm-project/vllm/
- https://github.com/vllm-project/vllm/issues/57719
- https://vuldb.com/vuln/413896/cti
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cach...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...