Description
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.
Affected products
internlm: lmdeploy
References5
- github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5… ExploitMitigationVendor Advisory
- github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5… ExploitMitigationVendor Advisory
- github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e063… Patch
- github.com/InternLM/lmdeploy/pull/4447 Issue TrackingPatch
- github.com/InternLM/lmdeploy/releases/tag/v0.12.3 Release Notes
Metrics
- CVSS 3.1
-
7.5
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - EPSS — exploit probability
- 45% percentile: 99 · as of 13 November 2026
- CWE
- CWE-918
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.