CVE-2026-46432: InternLM LMDeploy arbitrary code execution via hardcoded trust_remote_code

CVE-2026-46432 · Severity: high · CVSS 7.8 · Published 2026-06-10

LMDeploy is a toolkit used to compress and serve large language models (LLMs). A security flaw allows the software to automatically execute untrusted code embedded within a machine learning model during the loading process. If an attacker can influence which model the system loads, they can gain full control over the server, potentially stealing sensitive data, API keys, or interfering with AI operations.

Technologies: lmdeploy (PyPI). Vendors: PyPI.

Quick answers

Is CVE-2026-46432 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-46432 being exploited in the wild.
How severe is CVE-2026-46432?
High severity, with a CVSS score of 7.8, published 10 June 2026.
Which products and versions are affected?
lmdeploy (PyPI) < 0.13.0, ECOSYSTEM:introduced=0,fixed=0.13.0.
Is there a fix for CVE-2026-46432?
Yes. lmdeploy (PyPI): upgrade to 0.13.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-46432 attacked?
It is attacked with local access, in a software library.
Am I affected by CVE-2026-46432?
Check whether you run lmdeploy (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • lmdeploy (PyPI): upgrade to 0.13.0 or later
    pip install "lmdeploy>=0.13.0"

Technical details

LMDeploy (versions <= 0.12.3) hardcodes the 'trust_remote_code=True' parameter in multiple HuggingFace Transformers API call sites, specifically within 'lmdeploy/archs.py' and 'lmdeploy/utils.py'. This parameter allows HuggingFace models to execute arbitrary Python code defined in the model repository during initialization. An attacker who can influence the 'model_path'—via deployment configurations, CI/CD pipelines, or container settings—can point the service to a malicious repository. Upon loading, the malicious code executes with the privileges of the LMDeploy process, leading to full system compromise. As of publication, no patches are available.

Affected products

  • InternLM LMDeploy <= 0.12.3

Identifiers

  • CVE-2026-46432
  • GHSA-m549-qq94-fvhg
  • PYSEC-2026-2609

Timeline

  • 2026-05-15: advisory: GitHub Security Advisory published by researcher
  • 2026-06-10: disclosed: CVE published to NVD

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.