CVE-2026-63086 text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions
Unauthenticated attackers can force the server to make arbitrary HTTP requests, enabling internal port scanning and cloud metadata credential theft.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-63086?
CVE-2026-63086 is a medium-severity server-side request forgery vulnerability in huggingface text-generation-inference, published on 16 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-918
Which versions are affected by CVE-2026-63086?
How do I fix CVE-2026-63086?
No fix has been published for CVE-2026-63086 yet. Limit exposure of the affected software until one is available.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2026-63086 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-63086 exists.
Sources
Also known as GHSA-c6cx-mj2w-vjcr.