Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-9xq9-36w5-q796

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

CVSS 7.8 HighEPSS 0.0016 · 5th percentile

Published by the GitHub Advisory Database at 21 May 2026, 19:33 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
lmdeployPyPI<0.13.00.13.0
Identifiers
GHSA-9xq9-36w5-q796 · CVE-2026-46517 · PYSEC-2026-2608
Weakness (CWE)
CWE-94 · CWE-915 · CWE-1188
Tags
Published
21 May 2026
Updated
15 Sept 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

The lmdeploy package before 0.13.0 hardcodes trust_remote_code=True when loading model configs and some helper functions, with no user option to disable it. A user who runs lmdeploy against a malicious Hugging Face repository can have Python code from that repository executed on their machine. The source gives few details on the exact trigger conditions beyond this. Upgrade lmdeploy to 0.13.0 or later, which contains the fix.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
7.8 High 3.1 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0016, the 5th percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:10 UTC First seen by agentprime
  2. 31 Oct 2026, 14:10 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.