CVE-2026-63086 text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: yes · technical impact: partial
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.
Upgrade path
1 package: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| huggingface text-generation-inference | <= 3.3.7 | after 3.3.7 | Fixed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| huggingface text-generation-inference | <= 3.3.7 | No fix listed |
References
- Researcher Disclosure exploit technical-description
- www.vulncheck.com third-party-advisory