Vulnerability · Published Jun 9, 2026 · Assigned by GitHub_M
CVE-2026-46432LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
High 7.8
In plain English
A high-severity code injection in lmdeploy from InternLM. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 4% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Severity (CVSS 3.1)7.8High
Exploit odds (30 days)0.1%top 96.4% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | lmdeploy | 0.13.0 | GHSA-m549-qq94-fvhg |
| PyPI | lmdeploy | 0.13.0 | PYSEC-2026-2609 |
Affected products (as reported)
Weakness: CWE-94 · Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
References
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-m549-qq94-fvhg x_refsource_CONFIRM