CVE-2026-33626
high · 7.5A public exploit / detection template exists
Weaponised detection is publicly available, which meaningfully raises real-world risk regardless of CVSS. nuclei-templates →
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.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Weaknesses
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| internlm | lmdeploy | < 0.12.3 |
Check a specific version with /api/v1/cve/match.
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
Query this programmatically:
curl https://evil-db.io/api/v1/cve/CVE-2026-33626