Read the docs
TI-2026-64810 Aliases CVE-2026-100650GHSA-j8gm-f3cq-6c27

vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization

Priority MEDIUM 64CWE-400Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
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: 4 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 through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00808 57th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial vllm (vllm-project): 0.29.0Red Hat: 12 advisoriesRed Hat: 4 fixed, 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-projectvllmbefore 0.29.00.29.0Patch availableCNA
  • vllm Vendorvllm-project Affected before 0.29.0 Fixed in 0.29.0 Patch available CNA

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*up to 0.29.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions up to 0.29.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.29.0

Red Hat 12 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 9 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
  • RHSA-2026:90440 Released 2026-10-26 · Red Hat rating Important
    Red Hat Enterprise Linux AI 3.4.6 security update
    • Red Hat Enterprise Linux AI 3.4 registry.redhat.io/rhelai3/bootc-aws-cuda-rhel9, registry.redhat.io/rhelai3/bootc-azure-cuda-rhel9, registry.redhat.io/rhelai3/bootc-azure-rocm-rhel9 +3
  • RHSA-2026:90432 Released 2026-10-26 · Red Hat rating Important
    Red Hat Enterprise Linux AI 3.4.6 security update
    • Red Hat Enterprise Linux AI 3.4 registry.redhat.io/rhelai3/disk-image-cuda-rhel9
  • RHSA-2026:84734 Released 2026-10-19 · Red Hat rating Critical
    RHOAI 3.4.5 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 3.4 registry.redhat.io/rhoai/odh-ai-gateway-payload-processing-rhel9, registry.redhat.io/rhoai/odh-automl-rhel9, registry.redhat.io/rhoai/odh-autorag-rhel9 +47
  • RHSA-2026:83121 Released 2026-10-14 · Red Hat rating Important
    Red Hat AI Inference 3.4.6 (rocm)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-rocm-rhel9
  • RHSA-2026:83120 Released 2026-10-14 · Red Hat rating Important
    Red Hat AI Inference 3.4.6 (cuda)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-cuda-rhel9
  • RHSA-2026:83114 Released 2026-10-14 · Red Hat rating Important
    Red Hat AI Inference 3.4.6 (spyre)
    • Red Hat AI Inference Server 3.4 registry.redhat.io/rhaii/vllm-spyre-rhel9
  • RHSA-2026:83112 Released 2026-10-14 · Red Hat rating Important
    Red Hat AI Inference 3.4.6 (cpu)
    • Red Hat AI Inference Server 3.4 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 0.29.0

    6 records Highest priority Priority MEDIUM 2 MEDIUM, 4 LOW

    Other records, highest priority first

    • TI-2026-64811 vllm before 0.29.0 Denial of Service via Decoder Prompt Length BypassPriority MEDIUM 64
    • TI-2026-64808 vllm before 0.29.0 Uncontrolled Resource Consumption via Audio DecodingPriority LOW 36
    • TI-2026-64807 vLLM before 0.29.0 CPU Exhaustion via unbounded cache_saltPriority LOW 36
    Show all 6 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 planned: Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix planned: Will not fix
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet
Red Hat AI Inference Server 3.4Fixed RHSA-2026:83112, RHSA-2026:83114, RHSA-2026:83120, RHSA-2026:83121
Red Hat AI Inference Server 3.5Fixed RHSA-2026:94702, RHSA-2026:94709, RHSA-2026:94717, RHSA-2026:94721, RHSA-2026:94738
Red Hat Enterprise Linux AI 3.4Fixed RHSA-2026:90432, RHSA-2026:90440
Red Hat OpenShift AI 3.4Fixed RHSA-2026:84734
Not affected: 2 products
  • Red Hat OpenShift AI (RHOAI)
  • Red Hat OpenShift AI 3.4

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-100650
  2. 2026-10-03 Alias added: GHSA-j8gm-f3cq-6c27
  3. 2026-10-13 Affected versions changed · Red Hat
  4. 2026-10-14 EPSS moved to the 50th–90th percentile
  5. 2026-10-16 Fix available: RHSA-2026:83112 · Red Hat
  6. 2026-10-16 Fix available: RHSA-2026:83114 · Red Hat
  7. 2026-10-16 Fix available: RHSA-2026:83120 · Red Hat
  8. 2026-10-16 Fix available: RHSA-2026:83121 · Red Hat
  9. 2026-10-16 Fix available: Red Hat AI Inference Server 3.4 · Red Hat
  10. 2026-10-20 Fix available: RHSA-2026:84734 · Red Hat
  11. 2026-10-20 Fix available: Red Hat OpenShift AI 3.4 · Red Hat
  12. 2026-10-29 Fix available: Red Hat Enterprise Linux AI 3.4 · Red Hat
  13. 2026-10-30 Fix available: RHSA-2026:90432 · Red Hat
  14. 2026-10-30 Fix available: RHSA-2026:90440 · Red Hat
  15. 2026-10-30 Affected versions changed · Red Hat
  16. 2026-11-04 Fix available: RHSA-2026:94717 · Red Hat
  17. 2026-11-04 Fix available: RHSA-2026:94709 · Red Hat
  18. 2026-11-04 Fix available: RHSA-2026:94738 · Red Hat
  19. 2026-11-04 Fix available: RHSA-2026:94702 · Red Hat
  20. 2026-11-04 Fix available: RHSA-2026:94721 · Red Hat
  21. 2026-11-04 Fix available: Red Hat AI Inference Server 3.5 · Red Hat

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