Go to homepageCyberStrike

Menu

Star on GitHub · 3.4k
Sign inDownload

CVE-2026-100653

6.5 · MEDIUM

vLLM is an inference and serving engine for large language models.

Published Sep 26, 2026vllmCWE-348EPSS 0.34%

Overview

CVE-2026-100653 is a medium-severity vulnerability affecting vllm vllm. It was published on September 26, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).

This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

Technical description

vLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads for the FunAudioChat and Tarsier2 architectures: the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast loads in vllm/model_executor/models/funaudiochat.py and the Qwen2VLConfig.from_pretrained call used by Tarsier2ProcessingInfo in vllm/model_executor/models/qwen2_vl.py. As a result, deployments pinned to a reviewed revision still resolve these behavior-affecting processor, tokenizer, and config artifacts from the repository's default revision, so a later change to the upstream default branch can alter audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration without any change to the operator's configured pin. This is a supply-chain integrity and reproducibility failure for pinned deployments; it is residual to the ear

Remediation

Check the references section for vendor advisories and patches from vllm. Update vllm to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

Affected products

VendorProductVersionsStatus
vllmvllm>= 0.22.1, < 0.28.0Affected

References

GitHubgithub.com/vllm-project/vllm/commit/d26a28ab033697f55a1414b5b0435de7cd6045b6GitHubgithub.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628qRefwww.vulncheck.com/advisories/vllm-0.22.1-before-0.28.0-incomplete-artifact-pin-propagationGitHubgithub.com/vllm-project/vllm/security/advisories/GHSA-hhv2-872h-628q

How CyberStrike helps

Frequently asked questions

What is CVE-2026-100653?

CVE-2026-100653 is a medium-severity vulnerability affecting vllm vllm. It was published on September 26, 2026 and has a CVSS 3.1 base score of 6.5 (MEDIUM).

How severe is CVE-2026-100653?

This vulnerability has a CVSS 3.1 base score of 6.5, rated MEDIUM. It can be exploited remotely over the network. No authentication or special privileges are required for exploitation.

How do I fix or remediate CVE-2026-100653?

Check the references section for vendor advisories and patches from vllm. Update vllm to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.

How can CyberStrike help with CVE-2026-100653?

CyberStrike is an open-source, AI-augmented pentesting engine. Rather than flag a version number, it tests whether an issue like CVE-2026-100653 is actually reachable in your own applications and APIs, then verifies each finding before reporting it. That tells you if the weakness is a real, exploitable risk in your environment or a false positive you can safely deprioritize.

Related MEDIUM CVEs from 2026

View all
Browse by year2026202520242023202220212020201920182017201620152014201320122011201020092008200720062005200420032002200120001999
LiveWatch live →