CVE-2026-63086

published 16 Jul 2026 · updated 16 Jul 2026

text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions

9.6CriticalCVSS 8.6EPSS 0%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. No fixed version is recorded.

text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted image_url value in chat message content. The fetch_image function in router/src/validation.rs performs no validation of private, loopback, link-local, or cloud metadata target addresses, and the reqwest HTTP client follows redirects by default, enabling attackers to bypass scheme checks via redirect chains to reach internal services and cloud instance-metadata endpoints for internal port scanning and credential theft.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
huggingface<=3.3.7

Exploit evidence

1 public sources

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-63086 severity on Zeptric[![CVE-2026-63086](https://zeptric.io/badge/cve/CVE-2026-63086.svg)](https://zeptric.io/cve/CVE-2026-63086)