Path Traversal in Vllm-Project Vllm-Project/vllm
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`). 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.
Vulnerability class: Path Traversal (Directory Traversal)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.010 (61.2th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 61st percentile — 61.2% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.007 · newest: 0.010 · change: +0.002
Affected products
- Vllm-Project Vllm-Project/vllm — versions unspecified
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-4944?
- CVE-2026-4944 is a high-severity vulnerability in Vllm-Project Vllm-Project/vllm, classified under Path Traversal. CVSS score: 8.8/10. Published 2026-05-28.
- How severe is CVE-2026-4944?
- High severity. CVSS v3 base score is 8.8 out of 10.