vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
Priority MEDIUM 43CWE-693Published · Updated
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- Low
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Partial Red Hat: 5 fixed, 2 without a fix
Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-693.
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.
Why it matters now
Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.01369 72nd percentileScored 2026-11-07
Fix Partial vllm (vllm-project): 0.18.0vllm (PyPI): 0.18.0Red Hat: 12 advisoriesRed Hat: 5 fixed, 2 without a fix
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| vllm-project | vllm | 0.10.1 to before 0.18.0 | 0.18.0 | Patch available | CNA |
| — | vllm (PyPI) | 0.10.1 to before 0.18.0 | 0.18.0 | Patch available | GHSA-7972-pg2x-xr59 |
- vllm Vendorvllm-project Affected 0.10.1 to before 0.18.0 Fixed in 0.18.0 Patch available CNA
- vllm (PyPI) Vendor— Affected 0.10.1 to before 0.18.0 Fixed in 0.18.0 Patch available GHSA-7972-pg2x-xr59
Remediation
- Fix · CNA vllm (vllm-project) Fixed in 0.18.0
- Fix · GHSA-7972-pg2x-xr59 vllm (PyPI) Fixed in 0.18.0 Advisory →
Red Hat 12 advisories
- RHSA-2026:73987 Released 2026-09-30 · Red Hat rating CriticalRHOAI 3.3.7 - Red Hat OpenShift AI
- Red Hat OpenShift AI 3.3 registry.redhat.io/rhoai/odh-built-in-detector-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9, registry.redhat.io/rhoai/odh-data-science-pipelines-argo-argoexec-rhel9 +47
- RHSA-2026:42644 Released 2026-07-21 · Red Hat rating ImportantRHOAI 2.25.9 - Red Hat OpenShift AI
- Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-feature-server-rhel9, registry.redhat.io/rhoai/odh-kserve-storage-initializer-rhel9 +36
- RHSA-2026:37275 Released 2026-07-09 · Red Hat rating CriticalRHOAI 3.3.5 - Red Hat OpenShift AI
- Red Hat OpenShift AI 3.3 registry.redhat.io/rhoai/odh-dashboard-rhel9, registry.redhat.io/rhoai/odh-data-science-pipelines-operator-controller-rhel9, registry.redhat.io/rhoai/odh-feast-operator-rhel9 +45
Show 9 more Red Hat advisories
- RHSA-2026:24977 Released 2026-06-10 · Red Hat rating ImportantRHOAI 2.25.7 - Red Hat OpenShift AI
- Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-nlp-rhel9, registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9 +34
- RHSA-2026:19725 Released 2026-05-20 · Red Hat rating ImportantRed Hat AI Inference Server 3.2.2 (ROCm)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
- RHSA-2026:19724 Released 2026-05-20 · Red Hat rating ImportantRed Hat AI Inference Server 3.2.2 (CUDA)
- Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9
- RHSA-2026:19712 Released 2026-05-20 · Red Hat rating CriticalRHOAI 3.3.3 - Red Hat OpenShift AI
- Red Hat OpenShift AI 3.3 registry.redhat.io/rhoai/odh-built-in-detector-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9, registry.redhat.io/rhoai/odh-data-science-pipelines-argo-argoexec-rhel9 +33
- RHSA-2026:10141 Released 2026-04-23 · Red Hat rating ImportantRed Hat Enterprise Linux AI 3.3.1
- Red Hat Enterprise Linux AI 3.3 registry.redhat.io/rhelai3/disk-image-cuda-rhel9
- RHSA-2026:10140 Released 2026-04-23 · Red Hat rating ImportantRed Hat Enterprise Linux AI 3.3.1
- Red Hat Enterprise Linux AI 3.3 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-2026:8748 Released 2026-04-17 · Red Hat rating ImportantRed Hat AI Inference Server Model Optimization Tools 3.3.1 (CUDA)
- Red Hat AI Inference Server 3.3 registry.redhat.io/rhaiis/model-opt-cuda-rhel9
- RHSA-2026:8746 Released 2026-04-17 · Red Hat rating ImportantRed Hat AI Inference Server 3.3.1 (CUDA)
- Red Hat AI Inference Server 3.3 registry.redhat.io/rhaiis/vllm-cuda-rhel9
- RHSA-2026:8747 Released 2026-04-17 · Red Hat rating ImportantRed Hat AI Inference Server 3.3.1 (ROCm)
- Red Hat AI Inference Server 3.3 registry.redhat.io/rhaiis/vllm-rocm-rhel9
Vendor assessments
Red Hat
Red Hat rating: Important. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat AI Inference Server | Affected | No fix planned: Will not fix |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix planned: Will not fix |
| Red Hat AI Inference Server 3.2 | Fixed | RHSA-2026:19724, RHSA-2026:19725 |
| Red Hat AI Inference Server 3.3 | Fixed | RHSA-2026:8746, RHSA-2026:8747, RHSA-2026:8748 |
| Red Hat Enterprise Linux AI 3.3 | Fixed | RHSA-2026:10140, RHSA-2026:10141 |
| Red Hat OpenShift AI 2.25 | Fixed | RHSA-2026:24977, RHSA-2026:42644 |
| Red Hat OpenShift AI 3.3 | Fixed | RHSA-2026:19712, RHSA-2026:37275, RHSA-2026:73987 |
Not affected: 4 products
- Red Hat AI Inference Server
- Red Hat OpenShift AI (RHOAI)
- Red Hat OpenShift AI 2.25
- Red Hat OpenShift AI 3.3
Timeline
- 2026-10-02 Threatist record created from CVE-2026-27893
- 2026-10-03 Alias added: GHSA-7972-pg2x-xr59
- 2026-10-06 Affected versions changed · Red Hat
- 2026-10-07 Fix available: RHSA-2026:73987 · Red Hat
- 2026-10-07 Affected versions changed · Red Hat
- 2026-11-06 Fix available: RHSA-2026:42644 · Red Hat
References
Advisory 2
Other 16
- https://github.com/vllm-project/vllm/pull/36192
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json
- https://github.com/vllm-project/vllm
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml
- https://bugzilla.redhat.com/show_bug.cgi?id=2452055
- https://access.redhat.com/security/cve/CVE-2026-27893
- https://access.redhat.com/errata/RHSA-2026:8748
- https://access.redhat.com/errata/RHSA-2026:8747
- https://access.redhat.com/errata/RHSA-2026:8746
- https://access.redhat.com/errata/RHSA-2026:37275
- https://access.redhat.com/errata/RHSA-2026:24977
- https://access.redhat.com/errata/RHSA-2026:19725
- https://access.redhat.com/errata/RHSA-2026:19724
- https://access.redhat.com/errata/RHSA-2026:19712
- https://access.redhat.com/errata/RHSA-2026:10141
- https://access.redhat.com/errata/RHSA-2026:10140
More vllm-project vulnerabilities
- 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
Sources
- CVE-2026-27893 · CVE Program
- CVE-2026-27893 · NVD
- FIRST EPSS
- GHSA-7972-pg2x-xr59 · GitHub Advisory Database · CC BY 4.0
- CVE-2026-27893 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences