Read the docs
TI-2026-63478 Aliases CVE-2026-94623GHSA-g3cp-v4cp-9xfq

vLLM through 0.29.0 Denial of Service via NIXL Multi-Prompt Assertion Failure

Priority MEDIUM 45CWE-617Published · 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-617.

Summary

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00627 50th percentileScored 2026-11-07
Fix Partial Red Hat: 1 advisoryRed 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-projectvllmup to 0.29.0—No fix listedCNA
  • vllm Vendorvllm-project Affected up to 0.29.0 Fixed in — No fix listed 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

Red Hat 1 advisory

  • 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

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 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-2026-94623
  2. 2026-10-03 Alias added: GHSA-g3cp-v4cp-9xfq
  3. 2026-10-10 Affected versions changed · Red Hat
  4. 2026-10-20 Fix available: RHSA-2026:84734 · Red Hat
  5. 2026-10-20 Fix available: Red Hat OpenShift AI 3.4 · Red Hat
  6. 2026-10-30 EPSS moved to the 50th–90th percentile

References

Patch 1

Other 2

  • 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