8.8
CVE-2025-67729
- EPSS 0.07%
- Veröffentlicht 26.12.2025 21:54:10
- Zuletzt bearbeitet 31.12.2025 21:31:22
- Quelle security-advisories@github.com
- CVE-Watchlists
- Unerledigt
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 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.
Verknüpft mit AI von unstrukturierten Daten zu bestehenden CPE der NVD
Diese Information steht angemeldeten Benutzern zur Verfügung. 
Login
LoginDaten sind bereitgestellt durch National Vulnerability Database (NVD)
| Typ | Quelle | Score | Percentile |
|---|---|---|---|
| EPSS | FIRST.org | 0.07% | 0.211 |
| Quelle | Base Score | Exploit Score | Impact Score | Vector String |
|---|---|---|---|---|
| security-advisories@github.com | 8.8 | 2.8 | 5.9 |
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
|
CWE-502 Deserialization of Untrusted Data
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.