CVE-2026-4944
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedvllm-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.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceIn vllm-project/vllm version 0.14.1, the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`nemotron_vl.py` and `kimi_k25.py`), bypassing user-specified `--trust-remote-code=False` settings. This allows remote code execution when loading models from malicious HuggingFace repositories, as the hardcoded parameter overrides user configuration.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Check installed vllm versionRun 'pip show vllm' or 'python -c "import vllm; print(vllm.__version__)"' to get the installed versionAffected if Version is 0.14.1
-
Locate model implementation filesFind nemotron_vl.py and kimi_k25.py in the vllm installation directory, typically under vllm/model_executor/models/Affected if These files exist in the installed vllm package
-
Inspect nemotron_vl.py for hardcoded parameterSearch the file contents for 'trust_remote_code=True' as a hardcoded value in model loading codeAffected if The file contains 'trust_remote_code=True' that would override user settings
-
Inspect kimi_k25.py for hardcoded parameterSearch the file contents for 'trust_remote_code=True' as a hardcoded value in model loading codeAffected if The file contains 'trust_remote_code=True' that would override user settings
You are affected if using vllm 0.14.1 and either nemotron_vl.py or kimi_k25.py contains hardcoded trust_remote_code=True that bypasses your --trust-remote-code=False setting.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
From vendor dataRemove the hardcoded `trust_remote_code=True` from the affected files and ensure user-provided settings are respected, or upgrade to a patched version once available. Avoid loading untrusted models until the fix is applied.
- Consultation3.0 h
- Implementation3.0 h
- Testing4.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,360.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-4944 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-4944 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data