| Component | vLLM |
| Severity | medium (CVSS 5.3) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
| Published (NVD) | 2026-09-30 |
| Last modified | 2026-10-06 |
| Affected versions | vllm <= 0.26.0 |
| Fixed in | see the vendor advisory |
| Weakness | CWE-404 |
| CISA KEV | not listed |
NVD description
A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has been published and may be used. Upgrading to version 0.29.1rc0 is able to resolve this issue. This patch is called 3439bad37e68ba9755a46f4f6b44a4aeaf1f60a9. Upgrading the affected component is advised.
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-2026-103241
- https://github.com/vllm-project/vllm/commit/3439bad37e68ba9755a46f4f6b44a4aeaf1f60a9
- https://github.com/vllm-project/vllm/issues/50927
- https://github.com/vllm-project/vllm/pull/54303
- https://github.com/vllm-project/vllm/releases/tag/v0.29.1rc0
- https://vuldb.com/cve/CVE-2026-103241
- https://vuldb.com/submit/956250
- https://vuldb.com/vuln/411965
- https://gist.github.com/Yunzez/8e98d656aa667095b513161eb056d28e
- https://github.com/vllm-project/vllm/
- https://vuldb.com/vuln/411965/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 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 v...
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, 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...
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...