Skip to content
Fencer Vulns
high 7.8

CVE-2026-46517 json

LMDeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out

published 2026-05-21 5 mo ago modified 2026-09-15 55 d ago also EUVD-2026-35874 , GHSA-9xq9-36w5-q796 , PYSEC-2026-2608

cvss
7.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 5%
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, hardcoded "trust_remote_code=True" enables HF supply-chain RCE without user opt-in. Version 0.13.0 patches the issue.

Patch / fix

  • pypi lmdeploy 0.13.0

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
4 mo ago

Exploit prediction

0.16% chance of exploitation in the next 30 days, higher than 5% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

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

Affected packages

ecosystem package affected fixed in
pypi lmdeploy
<0.13.0
<=0.12.3
0.13.0

Affected products

  • InternLM lmdeploy

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code
  • CWE-915 Improperly Controlled Modification of Dynamically-Determined Object Attributes
  • CWE-1188 Initialization of a Resource with an Insecure Default

References

Sources

Fencer Vulns 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.