UTC
High

lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()

CVE-2025-67729 · GHSA-9pf3-7rrr-x5jh · published 2025-12-26 · updated 2025-12-27

Severity
High
CVSS score
8.8
Chance of exploitation (EPSS)
0.51%
Fixed in
0.11.1
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

An insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weightsonly=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. CWE:** CWE-502 - Deserialization of Untrusted Data ---

What to do

Upgrade lmdeploy to 0.11.1 or later.

Add weights_only=True to all torch.load() calls:

Affected
PackageRegistryAffectedFixed in
lmdeployPyPI<= 0.110.11.1

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].