INCIDENT MAP

Browse / AI Framework and Platform Flaws / CVE-2026-59707

LocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLs

CVE-2026-59707 ยท 2026-07-07 critical

Class
AI Framework and Platform Flaws (filed by a model that read the advisory)
Technique
Server-side request forgery
Affected
github.com/mudler/LocalAI (Go)
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
EPSS
1.4% chance of exploitation in 30 days

How it works, in short

An unauthenticated model-apply endpoint fetches attacker-supplied gallery URLs, letting callers make the server request internal addresses and see partial responses in errors. (Our summary, written by a model. The source text is below.)

Details

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

Source: GitHub Advisory Database, used under CC BY 4.0.