Skip to main content

CVE-2026-100653: Use of Less Trusted Source in vllm-project vllm

0
High
VulnerabilityCVE-2026-100653cvecve-2026-100653
Published: 09/26/2026 (09/26/2026, 13:23:22 UTC)
Source: CVE Database V5
Vendor/Project: vllm-project
Product: vllm

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 earlier fix tracked as GHSA-3ww4-5jv9-j5gm / CVE-2026-47155 and does not constitute remote code execution or a trust_remote_code=False bypass. The issue is fixed in version 0.28.0.

CVSS v4.0

Score 8.3high

Attack Vector
Network
Attack Complexity
High
Attack Requirements
Present
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
Low
Vuln. Integrity
High
Vuln. Availability
None
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

Affected software

vllm-project

vllm

Affected versions
>=0.22.1 <0.28.0
vllm
pkg:pypi/vllm
Affected versions
>=0.22.1 <0.28.0

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/26/2026, 14:02:47 UTC

Technical Analysis

In vLLM versions from 0.22.1 up to but not including 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads related to the FunAudioChat and Tarsier2 architectures. Specifically, the WhisperFeatureExtractor and speech_tokenizer PreTrainedTokenizerFast in funaudiochat.py and the Qwen2VLConfig.from_pretrained call in qwen2_vl.py do not respect the pinned revision. Consequently, these components load from the repository's default revision, allowing changes in the upstream default branch to affect audio preprocessing, speech tokenizer behavior, or Tarsier2 configuration despite the operator's pinned deployment. This is a supply-chain integrity and reproducibility failure residual to a prior fix (GHSA-3ww4-5jv9-j5gm / CVE-2026-47155). The vulnerability does not enable remote code execution or bypass trust_remote_code=False. The issue is resolved in vLLM 0.28.0.

Potential Impact

Deployments pinned to a specific model revision may inadvertently load processor, tokenizer, or configuration artifacts from the repository's default branch instead of the pinned revision. This undermines supply-chain integrity and reproducibility, potentially causing unexpected changes in audio preprocessing and model behavior without operator changes. There is no direct remote code execution or privilege escalation impact.

Mitigation Recommendations

Upgrade to vLLM version 0.28.0 or later, where this issue is fixed. No other mitigation is required as the vulnerability is resolved in this official fix.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-09-26T02:33:07.899Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6ab7c9a9f7a7c5410652fd3c

Added to database: 09/26/2026, 13:33:29 UTC

Last enriched: 09/26/2026, 14:02:47 UTC

Last updated: 09/27/2026, 03:03:42 UTC

Views: 12

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses