Vulnerability · Published Jul 16, 2026 · Assigned by VulnCheck

CVE-2026-63086text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions

High 8.6

In plain English

A high-severity server-side request forgery in text-generation-inference from huggingface. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 38% of all known vulnerabilities).

Severity (CVSS 3.1)8.6High

Exploit odds (30 days)0.4%top 62.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

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.

Affected products (as reported)

Vendor	Product	Versions
huggingface	text-generation-inference	0 – through 3.3.7

Weakness: CWE-918 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

References

Researcher Disclosure technical-description, exploit
https://www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-multimodal-chat-completions third-party-advisory