Read the docs
TI-2026-78668 Aliases CVE-2026-114055GHSA-gx7p-2j49-hfq4

Uncontrolled resource use in vLLM lets clients exhaust server memory

Priority MEDIUM 44CWE-400Published · Updated

Key facts

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

Attack profile from CVSS 4.0 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-400.

Summary

vLLM from 0.7.3 before 0.31.0 does not limit the multimodal processor parameters that remote clients set per request through mm_processor_kwargs. This is uncontrolled resource consumption (CWE-400). A remote attacker without privileges can set large image size, patch, crop or frame count values in processors such as Isaac and InternVL, exhausting memory and terminating the shared server.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

Description from the CNA

vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image size, patch count, crop count, or frame count values in Isaac, InternVL, H2OVL, and other processors to exhaust memory and terminate the shared server.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.0042 36th percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.31.0vllm (PyPI): 0.31.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
Yes
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-projectvllm0.7.3 to before 0.31.00.31.0Patch availableCNA
—vllm (PyPI)0.7.3 to before 0.31.00.31.0Patch availableGHSA-gx7p-2j49-hfq4
  • 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-gx7p-2j49-hfq4

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, the fixed version listed for the vllm-project and PyPI packages. Red Hat's plan for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI) is none available.

Written with Claude Haiku 5.5 from the sources below · 2026-10-28

  • Fix · CNA vllm (vllm-project) Fixed in 0.31.0
  • Fix · GHSA-gx7p-2j49-hfq4 vllm (PyPI) Fixed in 0.31.0 Advisory →

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-2026-78665 Memory exhaustion in vLLM MOSS-Audio serving through /tokenizePriority MEDIUM 44
    • TI-2026-78666 Remote code execution in vLLM via mm_processor_kwargs.code_revisionPriority MEDIUM 42
    • 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
Not affected: 1 product
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-10-21 Threatist record created from CVE-2026-114055
  2. 2026-10-21 CISA SSVC decision points changed
  3. 2026-10-22 Affected versions changed · Red Hat
  4. 2026-10-22 CVSS score added · Red Hat
  5. 2026-10-23 Affected versions changed · Red Hat
  6. 2026-10-23 Alias added: GHSA-gx7p-2j49-hfq4
  7. 2026-10-23 Fix available: PyPI/[email protected] · GHSA-gx7p-2j49-hfq4
  8. 2026-10-23 CVSS score added · GHSA-gx7p-2j49-hfq4
  9. 2026-10-23 Weakness changed · GHSA-gx7p-2j49-hfq4
  10. 2026-10-23 6 new references · GHSA-gx7p-2j49-hfq4

References

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