HighVulnerabilityLLM-specific

CVE-2025-67729: LMDeploy insecure deserialization when loading model checkpoint files

Source: NVD(opens in a new tab)
Identifier: CVE-2025-67729
Published: December 26, 2025
Record updated: October 9, 2026

Affected: lmdeploy <= 0.11
Fixed in: 0.11.1
released December 24, 2025, 2 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

CVE-2025-67729 affects LMDeploy, a toolkit for compressing, deploying, and serving LLMs, prior to version 0.11.1. The toolkit calls torch.load() without weights_only=True when loading model checkpoint files, which is an insecure deserialization flaw (CWE-502). Loading a malicious .bin or .pt model file lets an attacker execute arbitrary code on the victim's machine.

Mitigation

Fixed in 0.11.1.

Details

Scores and exploitation

CVSS score: 8.8(high)
Patch available: Yes
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-502
Attack pattern (CAPEC): CAPEC-586
AI threat technique (MITRE ATLAS): AML.T0010

Affected

Packages: lmdeploy@<= 0.11 (fixed: 0.11.1)

Classification

Attack type: Supply chain
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-67729

First tracked: February 15, 2026 at 08:53 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items