Read the docs
TI-2026-78666 Aliases CVE-2026-114053GHSA-h3rc-6mm3-gc2m

Remote code execution in vLLM via mm_processor_kwargs.code_revision

Priority MEDIUM 42CWE-94Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
Present
Impact type
Code execution
Confidentiality · integrity · availability
High · High · High
Fix status
Partial Red Hat: 1 fixed, 3 without a fix

Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-94.

Summary

vLLM from 0.7.3 before 0.31.0 forwards a request-supplied mm_processor_kwargs.code_revision value to Transformers AutoProcessor.from_pretrained, which selects the revision of a model's dynamic processor code when trust_remote_code is enabled. An attacker who controls a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to run arbitrary Python in the vLLM API process. The flaw is tracked as CWE-829, inclusion of functionality from an untrusted control sphere.

Written with Claude Haiku 5.5 from the sources below · 2026-11-04

Description from the CNA

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00462 40th percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.31.0vllm (PyPI): 0.31.0Red Hat: 5 advisoriesRed Hat: 1 fixed, 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Total

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-projectvllm0.7.3 to before 0.31.00.31.0Patch availableCNA
—vllm (PyPI)0.7.3 to before 0.31.00.31.0Patch availableGHSA-h3rc-6mm3-gc2m
  • vllm Vendorvllm-project Affected 0.7.3 to before 0.31.0 Fixed in 0.31.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.7.3 to before 0.31.0 Fixed in 0.31.0 Patch available GHSA-h3rc-6mm3-gc2m

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.7.3 to before 0.31.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.7.3 to before 0.31.0 Vulnerable ·vLLM

Remediation

Upgrade vLLM to 0.31.0 or later, which fixes the vllm-project and PyPI vllm packages. Red Hat AI Inference Server 3.5 is fixed by RHSA-2026:94738, RHSA-2026:94721, RHSA-2026:94717, RHSA-2026:94709 and RHSA-2026:94702. Red Hat states that no fix plan is available for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI).

Written with Claude Haiku 5.5 from the sources below · 2026-11-04

  • Fix · CNA vllm (vllm-project) Fixed in 0.31.0
  • Fix · GHSA-h3rc-6mm3-gc2m vllm (PyPI) Fixed in 0.31.0 Advisory →

Red Hat 5 advisories

  • RHSA-2026:94738 Released 2026-11-03 · Red Hat rating Critical
    Red Hat AI Inference 3.5.3 (CUDA)
    • Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-cuda-rhel9
  • RHSA-2026:94721 Released 2026-11-03 · Red Hat rating Critical
    Red Hat AI Inference Tech Preview 3.5.3 (Gaudi)
    • Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-gaudi-rhel9
  • RHSA-2026:94717 Released 2026-11-03 · Red Hat rating Critical
    Red Hat AI Inference 3.5.3 (Spyre)
    • Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-spyre-rhel9
Show 2 more Red Hat advisories
  • RHSA-2026:94709 Released 2026-11-03 · Red Hat rating Critical
    Red Hat AI Inference 3.5.3 (ROCm)
    • Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-rocm-rhel9
  • RHSA-2026:94702 Released 2026-11-03 · Red Hat rating Critical
    Red Hat AI Inference 3.5.3 (CPU)
    • Red Hat AI Inference Server 3.5 registry.redhat.io/rhaii/vllm-cpu-rhel9

Fixed in the same release

Records fixed by the same vendor advisory or release, as the CNA lists them.

  • Release ·

    vllm-project vllm 0.31.0

    7 records Highest priority Priority MEDIUM 3 MEDIUM, 4 LOW

    Other records, highest priority first

    • TI-2026-78668 Uncontrolled resource use in vLLM lets clients exhaust server memoryPriority MEDIUM 44
    • TI-2026-78665 Memory exhaustion in vLLM MOSS-Audio serving through /tokenizePriority MEDIUM 44
    • TI-2026-78664 Denial of service in vLLM via min_tokens in /inference/v1/generatePriority LOW 37
    Show all 7 records →

Vendor assessments

Red Hat

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

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet
Red Hat AI Inference Server 3.5Fixed RHSA-2026:94702, RHSA-2026:94709, RHSA-2026:94717, RHSA-2026:94721, RHSA-2026:94738
Not affected: 1 product
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-21 Threatist record created from CVE-2026-114053
  2. 2026-10-27 Alias added: GHSA-h3rc-6mm3-gc2m
  3. 2026-10-27 CISA SSVC decision points changed
  4. 2026-10-29 Affected versions changed · Red Hat
  5. 2026-10-29 CVSS score added · Red Hat
  6. 2026-11-04 Fix available: RHSA-2026:94717 · Red Hat
  7. 2026-11-04 Fix available: RHSA-2026:94709 · Red Hat
  8. 2026-11-04 Fix available: RHSA-2026:94738 · Red Hat
  9. 2026-11-04 Fix available: RHSA-2026:94702 · Red Hat
  10. 2026-11-04 Fix available: RHSA-2026:94721 · Red Hat
  11. 2026-11-04 Fix available: Red Hat AI Inference Server 3.5 · Red Hat

References

Patch 1

Advisory 2

Other 4

  • 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