Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · LocalAI

CVE-2026-59707: LocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLs

criticalCVSS 4.0 9.2 · 3.1 8.6GHSA-8c5q-hx4g-qq23

LocalAI contains an unauthenticated server-side request forgery vulnerability in the POST /models/apply endpoint that allows attackers to fetch arbitrary internal URLs. The endpoint passes unsanitized gallery URL fields directly to gallery.GetGalleryConfigFromURLWithContext without proper validation, enabling attackers to force the server to issue HTTP GET requests to private and loopback ranges with partial…

Published Jul 7, 2026 · Updated Oct 2, 2026

Affected packages

github.com/mudler/LocalAI

Ecosystem
Go
Affected
< 1.40.1-0.20260703213242-2cbb3c96b34d
Fixed in
1.40.1-0.20260703213242-2cbb3c96b34d
Check
go list -m github.com/mudler/LocalAI

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

LocalAI contains an unauthenticated server-side request forgery vulnerability in the POST /models/apply endpoint that allows attackers to fetch arbitrary internal URLs. The endpoint passes unsanitized gallery URL fields directly to gallery.GetGalleryConfigFromURLWithContext without proper validation, enabling attackers to force the server to issue HTTP GET requests to private and loopback ranges with partial response content leaked through error messages.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LocalAI vulnerabilities

All LocalAI entries