- CVSS
- HIGH · 7.5 v3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
- Published
- 2026-04-20
- Weakness
- CWE-918
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-33626
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.
References
- https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626
- https://github.com/InternLM/lmdeploy/pull/4447
- https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-33626 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.