CVE-2026-46432 LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
Attackers can execute arbitrary code by exploiting hardcoded trust_remote_code settings in LMDeploy's model initialization process.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-46432?
CVE-2026-46432 is a high-severity code injection vulnerability in InternLM lmdeploy, published on 9 Jun 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_code=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no publicly available patches.
Weakness: CWE-94
Which versions are affected by CVE-2026-46432?
3 open source packages ship an affected version, including lmdeploy.
| Package | Affected | Fixed in |
|---|---|---|
lmdeploy PyPI | All versions | 0.13.0 |
lmdeploy PyPI | All versions | 0.13.0 |
lmdeploy PyPI | All versions | 0.13.0 |
How do I fix CVE-2026-46432?
Upgrade lmdeploy to 0.13.0 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-46432 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-46432 exists.
Sources
Also known as GHSA-m549-qq94-fvhg, PYSEC-2026-2609.