LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

Summarylmdeploy hardcodes trustremotecode=True in multiple HuggingFace model-loading call sites.The affected code paths are in:textlmdeploy/archs.pylmdeploy/utils.pyThe vulnerable call sites pass trustremotecode=True into HuggingFace Transformers APIs such as AutoConfig.frompretrained,...

LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

SummaryA Server-Side Request Forgery SSRF vulnerability exists in LMDeploy's vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and...

PT-2026-59262

📋 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...

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,...

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

SummaryAn 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.CW...

PYSEC-2026-1579 InternLM LMDeploy code injection vulnerability

A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been declared as critical. Affected by this vulnerability is the function Open of the file lmdeploy/docs/en/conf.py. The manipulation leads to code injection. It is possible to launch the attack on the local host. The exploit has...

PYSEC-2026-1577 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...

InternLM LMDeploy code injection vulnerability

A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been declared as critical. Affected by this vulnerability is the function Open of the file lmdeploy/docs/en/conf.py. The manipulation leads to code injection. It is possible to launch the attack on the local host. The exploit has...

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...

lmdeploy (0.0.14) potentially affected by CVE-2024-8966 via gradio (4.0.0b15)

gradio PYPI version 4.0.0b15 is affected by a known vulnerability. The following packages have a transitive dependency on gradio and may be impacted: - lmdeploy 0.0.14 Source cves: CVE-2024-8966 Source advisory: OSV:PYSEC-2026-1410...

lmdeploy (0.0.14) potentially affected by CVE-2024-12217 via gradio (4.0.0b15)

gradio PYPI version 4.0.0b15 is affected by a known vulnerability. The following packages have a transitive dependency on gradio and may be impacted: - lmdeploy 0.0.14 Source cves: CVE-2024-12217 Source advisory: OSV:PYSEC-2026-1418...

lmdeploy (0.0.14) potentially affected by CVE-2026-49119 via gradio (4.0.0b15)

gradio PYPI version 4.0.0b15 is affected by a known vulnerability. The following packages have a transitive dependency on gradio and may be impacted: - lmdeploy 0.0.14 Source cves: CVE-2026-49119 Source advisory: OSV:GHSA-J36P-7W88-G82J...

lmdeploy (0.0.14) potentially affected by CVE-2026-49119 via gradio (4.0.0b15)

gradio PYPI version 4.0.0b15 is affected by a known vulnerability. The following packages have a transitive dependency on gradio and may be impacted: - lmdeploy 0.0.14 Source cves: CVE-2026-49119 Source advisory: OSV:PYSEC-2026-2179...

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 via the model initialization process when trustremotecode=True is hardcoded in multiple HuggingFace model-loading call sites. An attacker can execute arbitrary code by supplying a malicious model repository...

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...

CVE-2026-46517

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trustremotecode=True" enables HF supply-chain RCE without user opt-in. Version 0.13.0 patches the issue...

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...

CVE-2026-46432: Improper Control of Generation of Code

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...

lmdeploy: Code injection vulnerability

lmdeploy is a toolkit developed by InternLM for compressing, deploying, and serving LLMs. Versions of lmdeploy prior to 0.12.3 have a code injection vulnerability. This vulnerability stems from the hardcoding of trustremotecode=True at multiple HuggingFace model loading points, which may allow...