Read the docs
TI-2026-80523 Aliases CVE-2026-115918GHSA-x567-49g5-p4cf

vLLM Responses API bypasses chat template trust setting

Priority LOW 29CWE-400Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
Denial of service
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-400.

Summary

vLLM versions from 0.16.0 before 0.32.0 are affected. The /v1/responses endpoint keeps a caller-supplied chat template when no server template is configured, which bypasses the trust_request_chat_template setting (CWE-400). An authenticated remote attacker with low privileges can exhaust CPU or memory through Jinja template rendering.

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

Description from the CNA

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.0035 28th percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.32.0vllm (PyPI): 0.32.0Red 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-projectvllm0.16.0 to before 0.32.00.32.0Patch availableCNA
—vllm (PyPI)0.16.0 to before 0.32.00.32.0Patch availableGHSA-x567-49g5-p4cf
  • vllm Vendorvllm-project Affected 0.16.0 to before 0.32.0 Fixed in 0.32.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.16.0 to before 0.32.0 Fixed in 0.32.0 Patch available GHSA-x567-49g5-p4cf

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.16.0 to before 0.32.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.16.0 to before 0.32.0 Vulnerable ·vLLM

Remediation

Upgrade the vllm package on PyPI to version 0.32.0. Red Hat lists no available plan for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI).

Written with Claude Haiku 5.5 from the sources below · 2026-10-30

  • Fix · CNA vllm (vllm-project) Fixed in 0.32.0
  • Fix · GHSA-x567-49g5-p4cf vllm (PyPI) Fixed in 0.32.0 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. 2026-10-26 Threatist record created from CVE-2026-115918
  2. 2026-10-27 Affected versions changed · Red Hat
  3. 2026-10-27 CVSS score added · Red Hat
  4. 2026-10-27 Priority changed: MEDIUM → LOW
  5. 2026-10-28 Alias added: GHSA-x567-49g5-p4cf
  6. 2026-10-28 Fix available: PyPI/[email protected] · GHSA-x567-49g5-p4cf
  7. 2026-10-28 CVSS score added · GHSA-x567-49g5-p4cf
  8. 2026-10-28 Weakness changed · GHSA-x567-49g5-p4cf
  9. 2026-10-28 6 new references · GHSA-x567-49g5-p4cf
  10. 2026-10-30 CISA SSVC decision points changed

References

Patch 3

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