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

July 7, 2026 (updated October 2, 2026)

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

github.com/advisories/GHSA-8c5q-hx4g-qq23
github.com/mudler/LocalAI/commit/f9b968e19d7cbc556d59dceb2e0e450b828a3fda
github.com/mudler/LocalAI/issues/10665
nvd.nist.gov/vuln/detail/CVE-2026-59707
www.vulncheck.com/advisories/localai-server-side-request-forgery-via-post-models-apply

Code Behaviors & Features

Detect and mitigate CVE-2026-59707 with GitLab Dependency Scanning

Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →