LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading (InternLM lmdeploy)

CVE-2026-33626
HIGH 7.5

At a glance

Source
NVD
EPSS
EPSS 45.25 % · percentile 99 ()
State
PUBLISHED
Published
Updated
Assigner
GitHub_M
NVD status
Analyzed

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.

Weaknesses (CWE)

  • CWE-918 — Server-Side Request Forgery

References

Scores

VersionScoreVectorScored by
CVSS 3.1HIGH 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NGitHub_M
CVSS 3.1HIGH 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NNVD · security-advisories@github.com (Secondary)

Advisories

European references

Affected configurations (NVD CPE)

Affected products

ProductVersions
InternLM · lmdeployaffected < 0.12.3

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD