Server-Side Request Forgery (SSRF) in Text Generation Web UI - #VU127415
Published: April 24, 2026
Text Generation Web UI
Detailed vulnerability description
The vulnerability allows a remote user to access internal network resources and disclose sensitive information.
The vulnerability exists due to server-side request forgery (SSRF) in the OpenAI-compatible multimodal image fetching functionality when processing attacker-controlled image_url values in API requests. A remote user can send a specially crafted request containing an arbitrary image_url to access internal network resources and disclose sensitive information.
The issue affects the OpenAI-compatible endpoints POST /v1/chat/completions and POST /v1/completions, and can reach loopback, private-network, or metadata endpoints depending on deployment.