Read the docs

Decompression-bomb guard bypass in vLLM Nemotron-VL processors

Priority MEDIUM 43CWE-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: 1 fixed, 3 without a fix

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

Summary

vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption flaw (CWE-400) because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None, which removes the decompression-bomb size limit. An unauthenticated remote attacker can submit a pathological image to /v1/chat/completions to exhaust memory, kill the worker and deny service to co-tenants.

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

Description from the CNA

vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers can submit a pathological decompression-bomb image to /v1/chat/completions to OOM-kill the worker and deny service to co-tenants.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00291 21st percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.25.0Red Hat: 5 advisoriesRed Hat: 1 fixed, 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-projectvllm0.10.2 to before 0.25.00.25.0Patch availableCNA
  • vllm Vendorvllm-project Affected 0.10.2 to before 0.25.0 Fixed in 0.25.0 Patch available CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.10.2 to before 0.25.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.10.2 to before 0.25.0 Vulnerable ·vLLM

Remediation

Upgrade vLLM to 0.25.0 or later. Red Hat fixes Red Hat AI Inference Server 3.5 in RHSA-2026:94738 (CUDA), RHSA-2026:94721 (Gaudi), RHSA-2026:94717 (Spyre), RHSA-2026:94709 (ROCm) and RHSA-2026:94702 (CPU). Red Hat's plan for 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 · 2026-11-04

  • Fix · CNA vllm (vllm-project) Fixed in 0.25.0

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

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. 2026-10-25 Threatist record created from CVE-2026-116177
  2. 2026-10-25 Affected versions changed · Red Hat
  3. 2026-10-25 CVSS score added · Red Hat
  4. 2026-10-26 Affected versions changed · Red Hat
  5. 2026-10-26 Priority changed: MEDIUM → LOW
  6. 2026-10-27 Alias added: GHSA-p9gm-63qh-x2pq
  7. 2026-10-29 CISA SSVC decision points changed
  8. 2026-10-29 Priority changed: LOW → MEDIUM
  9. 2026-11-04 Fix available: RHSA-2026:94717 · Red Hat
  10. 2026-11-04 Fix available: RHSA-2026:94709 · Red Hat
  11. 2026-11-04 Fix available: RHSA-2026:94738 · Red Hat
  12. 2026-11-04 Fix available: RHSA-2026:94702 · Red Hat
  13. 2026-11-04 Fix available: RHSA-2026:94721 · Red Hat
  14. 2026-11-04 Fix available: Red Hat AI Inference Server 3.5 · Red Hat

References

  • 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