Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- Low
- Impact type
- —
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- No fix listed
Attack profile from CVSS 3.0 · CNA. Fix status from CNA and Red Hat.
Summary
vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- 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-project/vllm | up to latest | — | No fix listed | CNA |
- vllm-project/vllm Vendorvllm-project Affected up to latest Fixed in — No fix listed CNA
Remediation
No fixed version listed by the sources yet.
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 yet |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix planned: Will not fix |
Not affected: 3 products
- Red Hat AI Inference Server
- Red Hat Enterprise Linux AI (RHEL AI) 3
- Red Hat OpenShift AI (RHOAI)
Timeline
- 2026-10-02 Threatist record created from CVE-2026-4944
- 2026-10-03 Alias added: GHSA-g57c-wgqx-8wx7
- 2026-10-07 Affected versions changed · Red Hat
- 2026-10-18 Affected versions changed · Red Hat
References
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-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
- TI-2026-04816 Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm CVSS 3.0HIGH 7.5
Sources
- CVE-2026-4944 · CVE Program
- CVE-2026-4944 · NVD
- FIRST EPSS
- GHSA-g57c-wgqx-8wx7 · GitHub Advisory Database · CC BY 4.0
- CVE-2026-4944 · 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