Read the docs
TI-2026-68365 Aliases CVE-2026-105754GHSA-ph72-cqr5-qpp7

Unvalidated multimodal inputs in vLLM disaggregated scale-out path

Priority LOW 28CWE-1284Published · Updated

Key facts

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

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-617 and CWE-639.

Summary

vLLM before 0.30.0 is affected. The /inference/v1/generate endpoint in the scale-out disaggregated path accepts caller-supplied multimodal features without checking them against the active model renderer contract (CWE-20). A remote attacker with low privileges can send malformed features that terminate the shared EngineCore. Forged cache hashes can also poison or retrieve cross-request encoder-cache state.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Description from the CNA

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00269 19th percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.30.0vllm (PyPI): 0.30.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
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 0.30.00.30.0Patch availableCNA
—vllm (PyPI)before 0.30.00.30.0Patch availableGHSA-ph72-cqr5-qpp7
  • vllm Vendorvllm-project Affected before 0.30.0 Fixed in 0.30.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected before 0.30.0 Fixed in 0.30.0 Patch available GHSA-ph72-cqr5-qpp7

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*before 0.30.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions before 0.30.0 Vulnerable ·vLLM

Remediation

Upgrade the vLLM PyPI package to version 0.30.0. Red Hat lists Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI) as affected with no fix and no plan available.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

  • Fix · CNA vllm (vllm-project) Fixed in 0.30.0
  • Fix · GHSA-ph72-cqr5-qpp7 vllm (PyPI) Fixed in 0.30.0 Advisory →

Vendor assessments

Red Hat

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

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)AffectedNo fix yet: Fix deferred

Timeline

  1. 2026-10-06 Threatist record created from CVE-2026-105754
  2. 2026-10-06 Alias added: GHSA-ph72-cqr5-qpp7
  3. 2026-10-06 Fix available: PyPI/[email protected] · GHSA-ph72-cqr5-qpp7
  4. 2026-10-06 CVSS score added · GHSA-ph72-cqr5-qpp7
  5. 2026-10-06 Weakness changed · GHSA-ph72-cqr5-qpp7
  6. 2026-10-06 5 new references · GHSA-ph72-cqr5-qpp7
  7. 2026-10-06 Affected versions changed · Red Hat
  8. 2026-10-06 CVSS score added · Red Hat
  9. 2026-10-07 Priority changed: MEDIUM → LOW
  10. 2026-10-08 CISA SSVC decision points changed

References

Patch 2

Advisory 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