CVE-2026-4944
Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control
- State
- Published
- Severity
- 8.8 High
- Published
- May 28, 2026
- Updated
- May 28, 2026
- Reserved
- Mar 26, 2026
Description
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.0 | 8.8 High | CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | @huntr_ai |
Weaknesses
- CWE-22 Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Affected Products
| Product | Versions |
|---|---|
vllm-project/vllmvllm-project |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.