Cyber Resilience

CVE-2025-67729

RCE in Internlm Lmdeploy ≤ 0.11.1

Published
26 December 2025
Modified
31 December 2025
Patch / advisory
CVSS Score v3.1 8.8
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS Score 0.0053 42th percentile
Risk Priority 64 floored blend · peak EPSS

Summary

CVE-2025-67729 is a high-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Internlm Lmdeploy. Its CVSS base score is 8.8 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 42th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2025-67729 is an insecure deserialization vulnerability (CWE-502) in LMDeploy, an open-source toolkit for compressing, deploying, and serving large language models (LLMs). Affecting versions prior to 0.11.1, the flaw occurs when the torch.load() function is invoked without the weights_only=True parameter during the loading of model checkpoint files in .bin or .pt formats. This enables remote code execution upon processing malicious files, earning a CVSS v3.1 base score of 8.8 (AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H).

The vulnerability can be exploited by any remote attacker who tricks a user into loading a specially crafted .bin or .pt model file into an affected LMDeploy instance. Exploitation requires user interaction, such as manually loading a model from an untrusted source, but needs no privileges. Successful attacks grant attackers arbitrary code execution on the victim's machine with the privileges of the LMDeploy process, potentially leading to full system compromise, data theft, or further lateral movement.

The issue has been addressed in LMDeploy version 0.11.1, where the patch enforces the weights_only=True parameter in torch.load() calls. Official advisories, including GHSA-9pf3-7rrr-x5jh on the project's GitHub security page and the fixing commit eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee, recommend immediate upgrades and caution against loading models from untrusted sources.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms

Related Threats

MITRE ATT&CK Enterprise Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-3162Same product: Internlm Lmdeploy
CVE-2026-63764Same product: Internlm Lmdeploy
CVE-2026-33626Same product: Internlm Lmdeploy
CVE-2025-3163Same product: Internlm Lmdeploy
CVE-2026-31239Shared CWE-502
CVE-2025-14924Shared CWE-502
CVE-2025-14929Shared CWE-502
CVE-2025-14920Shared CWE-502
CVE-2026-1839Shared CWE-502
CVE-2025-14930Shared CWE-502

Affected Assets

internlm
lmdeploy
≤ 0.11.1

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can uncover deserialization flaws before deployment.

Input validation directly stops deserialization of untrusted data by ensuring inputs are valid before processing.

Engineering principles such as safe deserialization and input sanitization structurally prevent the weakness from being introduced.

Integrity verification tools can detect malformed or tampered serialized data after the fact.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-02 none match
prevents

PR.PS-02 addresses only post-deployment updates/patching and cannot prevent introduction of unsafe deserialization code, yet it can remediate some instances when the flaw exists in outdated libraries or components.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing includes validation of deserialization routines and the use of untrusted data, reducing the likelihood that unsafe object reconstruction will be deployed.

prevents

Requiring vetted libraries, regular updates and SAST before release reduces the likelihood that deserialization logic will accept and act on attacker-controlled serialized objects.

finds

Regular scanning of third-party libraries and timely patching reduce the likelihood that unsafe deserialization vulnerabilities remain active.

none

Mandatory malware scanning of data received over networks or storage media intercepts malicious serialized payloads before they are deserialized by the target application.

References