CVE-2026-4944
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`).
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.75%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.0
- 8.8 HIGHCVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.75% probability · 53th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-22
- Source
- security@huntr.dev
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.