Skip to content
Fencer Intel
high 7.8

CVE-2026-46432 json

LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

published 5mo ago modified 3mo ago also EUVD-2026-35873 , GHSA-m549-qq94-fvhg , PYSEC-2026-2609

cvss
7.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.1%
EPSS 0.1% chance of exploitation in 30 days, percentile 3%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi lmdeploy 0.13.0

Is CVE-2026-46432 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
5mo ago

Exploit prediction

0.14% chance of exploitation in the next 30 days, higher than 3% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/InternLM/lmdeploy/security/advisories/GHSA-m549-qq94-fvhg referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
GitHub 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
OSV 3.1 7.8 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi lmdeploy
<0.13.0
0.13.0

Affected products

  • InternLM lmdeploy

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.