Skip to content
Fencer Vulns
high 8.8

CVE-2026-27893 json

vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

published 2026-03-26 7 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-16478 , GHSA-7972-pg2x-xr59 , PYSEC-2026-2297

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.4%
EPSS 1.4% chance of exploitation in 30 days, percentile 72%
public exploits
0
none known

Summary

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

Patch / fix

  • pypi vllm 0.18.0
  • Red Hat Red Hat AI Inference Server 3.2 1779223651, 1779223654
  • Red Hat Red Hat AI Inference Server 3.3 1775680192, 1775680262, 1775749857
  • Red Hat Red Hat Enterprise Linux AI 3.3 1776773390, 1776773505, 1776871984, 1776871985, 1776871987, 1776872005, 1776938871
  • Red Hat Red Hat OpenShift AI 2.25 1780069069, 1782397826, 1783998774, 1783998857
  • Red Hat Red Hat OpenShift AI 3.3 1778600187, 1782996080

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-27893 updated cvss 8.8

vllm: vLLM: Remote code execution due to hardcoded trust_remote_code setting

  • Red Hat AI Inference Server rhaii/vllm-tpu-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaii/vllm-gaudi-rhel9, rhaii/vllm-neuron-rhel9, rhaiis/vllm-spyre-rhel9, +1 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-gaudi-rhel9
    affected: workaround, no fix planned “Will not fix”
  • Red Hat AI Inference Server 3.2 rhaiis 1779223651, rhaiis 1779223654
    fixed: vendor fix RHSA-2026:19724
  • Red Hat AI Inference Server 3.3 rhaiis 1775680192, rhaiis 1775680262, rhaiis 1775749857
    fixed: vendor fix RHSA-2026:8748
  • Red Hat Enterprise Linux AI 3.3 rhelai3 1776773390, rhelai3 1776773505, rhelai3 1776871984, rhelai3 1776871985, rhelai3 1776871987, rhelai3 1776872005, +1 more
    fixed: vendor fix RHSA-2026:10140
  • Red Hat OpenShift AI 2.25 rhoai/odh-vllm-cpu-rhel9 1782397826, rhoai/odh-vllm-cuda-rhel9 1783998774, rhoai/odh-vllm-rocm-rhel9 1783998857, rhoai/odh-vllm-gaudi-rhel9 1780069069
    fixed: vendor fix RHSA-2026:42644
  • Red Hat OpenShift AI 3.3 rhoai 1778600187, rhoai/odh-vllm-cpu-rhel9 1782996080, rhoai/odh-vllm-cpu-rhel9 1790274961
    fixed: vendor fix RHSA-2026:73987
  • Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-cuda-rhel9, rhaii/vllm-rocm-rhel9, rhaii/vllm-spyre-rhel9, rhaiis-preview/vllm-cuda-rhel9
    not affected: vulnerable code not present
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9
    not affected: vulnerable code not in execute path
show 1 more
  • Red Hat OpenShift AI 2.25 rhoai/odh-rhel9-operator 1780513840, rhoai/odh-rhel9-operator 1784004914, rhoai/odh-vllm-cpu-rhel9 1780069252, rhoai/odh-dashboard-rhel9 1780467029, rhoai/odh-dashboard-rhel9 1782826282, rhoai/odh-modelmesh-rhel9 1780069506, +143 more Red Hat OpenShift AI 3.3 rhoai 1778239104, rhoai 1778262829, rhoai 1778262856, rhoai 1778262893, rhoai 1778262907, rhoai 1778262952, +239 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
7 mo ago

Exploit prediction

1.37% chance of exploitation in the next 30 days, higher than 72% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CISA ADP 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
GitHub 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
OSV 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.10.1, <0.18.0
0.18.0

Affected products

  • vllm-project vllm
  • Red Hat Red Hat AI Inference Server 3.2
  • Red Hat Red Hat AI Inference Server 3.3
  • Red Hat Red Hat Enterprise Linux AI 3.3
  • Red Hat Red Hat OpenShift AI 2.25
  • Red Hat Red Hat OpenShift AI 3.3
  • Red Hat Red Hat AI Inference Server
  • Red Hat Red Hat OpenShift AI (RHOAI)

Classification

Weakness
  • CWE-693 Protection Mechanism Failure
  • CWE-501 Trust Boundary Violation

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.