CVE-2026-63086: text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions
huggingface · text-generation-inference
Affected: huggingface text-generation-inference · Exploitation: unlikely (under 1%)
Not in CyberSIXT coverage yet: no article names this CVE. This page shows the public record.
Higher than 38% of scored CVEs
DescriptionCVE.org
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 products1
From the CVE record. A product or version that is not listed is unknown, not unaffected.
- huggingface · text-generation-inferenceup to and including 3.3.7
On the Atlas
Every published CVE is on the CyberSIXT Atlas, grouped by weakness, vendor and month.
- Exploitation
- Unlikely (under 1%). EPSS under 1%, or no score yet.
- CISA KEV
- Not listed
- Public check
- No public nuclei template
- Weakness
- Server-Side Request Forgery
- Vendor
- huggingface
- Published
- July 2026
CoverageNo articles yet
No CyberSIXT article names CVE-2026-63086 yet, so there is no coverage timeline, action brief or change log for it. Everything on this page comes from the public CVE record, CISA KEV, EPSS and the nuclei template index. Search the archive or see the CVEs in the news.