SSRF in Huggingface Text-Generation-Inference
CVE-2026-63086
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.
Vulnerability class: SSRF (Server-Side Request Forgery)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.6 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N.
EPSS exploit prediction
EPSS: 0.004 (36.7th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 37th percentile — 36.7% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.004 · newest: 0.004 · change: 0.000
Affected products
- Huggingface Text-Generation-Inference — versions 0
Weakness classification (CWE)
References
- github.com/geo-chen/oss/blob/main/text-generation-inference.md (technical-description, exploit)
- www.vulncheck.com/advisories/text-generation-inference-ssrf-via-fetch-image-in-… (third-party-advisory)
Frequently asked questions
- What is CVE-2026-63086?
- CVE-2026-63086 is a high-severity vulnerability in Huggingface Text-Generation-Inference, classified under Server-Side Request Forgery (SSRF). CVSS score: 8.6/10. Published 2026-07-16.
- How severe is CVE-2026-63086?
- High severity. CVSS v3 base score is 8.6 out of 10.