CVE-2026-46517 LMDeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out
Hardcoded trust_remote_code setting allows remote code execution via Hugging Face supply chain without user consent.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-46517?
CVE-2026-46517 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, and only if a user opens a file or follows a link.
Official description
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. Version 0.13.0 patches the issue.
Which versions are affected by CVE-2026-46517?
3 open source packages ship an affected version, including lmdeploy.
| Package | Affected | Fixed in |
|---|---|---|
lmdeploy PyPI | All versions to 0.12.3 | None |
lmdeploy PyPI | All versions | 0.13.0 |
lmdeploy PyPI | All versions | 0.13.0 |
How do I fix CVE-2026-46517?
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-2026-46517 being exploited?
There is no known exploitation of CVE-2026-46517 in the wild and no public exploit code.
Sources
Also known as GHSA-9xq9-36w5-q796, PYSEC-2026-2608.