CVE-2025-67729HIGH 8.8EPSS p38.0%

CVE-2025-67729CVE-2025-67729

Description

LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1.

Scoring

CVSS 3.18.8 (HIGH)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS0.49% probability of exploitation · percentile 38.0% · 2026-06-19T12:03:05Z
Published2025-12-26
Last modified2025-12-31

Underlying weaknesses· 1

CWE-502

References

  1. https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee
  2. https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh
  3. https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh

1

TypeTargetConfidenceTier
WeaknessDeserialization of Untrusted Datacwe-5020%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2026-46432
CVE
CVE-2025-24357
CVE
CVE-2026-31214
CVE
CVE-2026-46517
CVE
CVE-2025-45146
CVE
CVE-2025-32434
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.