PT-2026-59263

Summary lmdeploy hardcodes trust remote code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trust remote code=True into HuggingFace Transformers APIs such as AutoConfig.from pretrained,...

CVE-2026-46432

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 "trustremotecode=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no...

Arbitrary Code Injection

Overview Affected versions of this package are vulnerable to Arbitrary Code Injection due to the hardcoded trustremotecode parameter being set to True, which allows remote code to be executed without user opt-in. An attacker can execute arbitrary code by supplying a malicious remote model...

PT-2026-42632

Summary lmdeploy hardcodes trust remote code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trust remote code=True into HuggingFace Transformers APIs such as AutoConfig.from pretrained,...

PT-2026-42614

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "get model arch and related helpers hardcode trust remote code=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this...

CVE-2025-67729

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 weightsonly=True parameter when loading model checkpoint files. This allows an attacker to execute...

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

Summary 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...

Insecure Deserialization

lmdeploy is vulnerable to Insecure Deserialization. The vulnerability is due to unsafe handling in the loadweightckpt of the file lmdeploy/lmdeploy/vl/model/utils.py of the component PT File Handler, allowing local attackers to exploit it...

LMDeploy Improper Input Validation Vulnerability

A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been classified as critical. Affected is the function loadweightckpt of the file lmdeploy/lmdeploy/vl/model/utils.py of the component PT File Handler. The manipulation leads to deserialization. Attacking locally is a requirement...