Read the docs
TI-2026-64813 Aliases CVE-2026-100653GHSA-r3cf-2wgr-7xh9

vLLM 0.22.1 before 0.28.0 Incomplete Artifact Pin Propagation

Priority HIGH 69CWE-348Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
High
Attack requirements
Present
Impact type
—
Confidentiality · integrity · availability
Low · High · None
Fix status
Partial Red Hat: 3 without a fix

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.0034 27th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial vllm (vllm-project): 0.28.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllm0.22.1 to before 0.28.00.28.0Patch availableCNA
  • vllm Vendorvllm-project Affected 0.22.1 to before 0.28.0 Fixed in 0.28.0 Patch available CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.22.1 to before 0.28.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.22.1 to before 0.28.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.28.0

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet: Fix deferred

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-100653
  2. 2026-10-03 Alias added: GHSA-r3cf-2wgr-7xh9

References

Exploit 1

Patch 1

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences