LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The load_image() 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 sensitive resources. Version 0.12.3 patches the issue.
Exploitability
AV:NAC:LPR:NUI:NScope
S:UImpact
C:HI:NA:N7.5/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NInput Validation