Code InjectionWeakness · CWE-94

CVE-2026-46517

HIGH · 7.8 CVSS v3.1 Published 2026-06-10
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
81/100
Remediation priority · High
No privileges

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 · unedited
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trust_remote_code=True" enables HF supply-chain RCE without user opt-in. At time of publication, there are no publicly available patches.

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 confidence

LMDeploy versions 0.12.3 and prior contain a hardcoded 'trust_remote_code=True' setting that enables arbitrary code execution when loading models from remote HuggingFace repositories. This supply-chain vulnerability allows attackers to achieve RCE by serving malicious models without requiring any user opt-in or explicit consent.

MitigationUntil a patch is available, avoid loading models from untrusted or unverified remote sources, and explicitly set trust_remote_code=False when using HuggingFace model loading functions. Audit existing deployments for usage of LMDeploy with remote model sources.

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
Local
Complexity
Low
Privileges
None
User interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:L/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 checks

Work through these to decide whether this CVE applies to you.

  1. Check if LMDeploy is installed
    Run 'pip show lmdeploy' or 'pip list | grep lmdeploy' to find the installed version
    Affected if LMDeploy version 0.12.3 or lower is installed and used to load HuggingFace models
  2. Compare installed version to affected range
    Verify the version number from step 1 against the affected versions (0.12.3 and prior)
    Affected if The installed version is 0.12.3 or any version lower than 0.12.3
  3. Identify LMDeploy usage with HuggingFace models
    Search project code, scripts, or configuration files for lmdeploy imports and model loading calls, particularly involving HuggingFace model repositories
    Affected if LMDeploy is being used to load models from HuggingFace Hub or similar remote sources
  4. Check trust_remote_code configuration
    Inspect any LMDeploy configuration files, environment variables, or model loading code for explicit trust_remote_code=False settings
    Affected if trust_remote_code is not explicitly set to False anywhere in the loading chain, meaning the hardcoded default applies

A user is affected if LMDeploy version 0.12.3 or prior is installed and is used to load HuggingFace models without trust_remote_code explicitly set to False.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

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 data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Until a patch is available, avoid loading models from untrusted or unverified remote sources, and explicitly set trust_remote_code=False when using HuggingFace model loading functions. Audit existing deployments for usage of LMDeploy with remote model sources.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation4.0 h
  • Testing4.0 h
  • Review / QA2.0 h
12.0 hours of engineering $2,080
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,328.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-46517 — 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 sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-46517 in production — separate from our analysis above.

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.

What this is

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.

What belongs here
  • 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