Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
huggingface text-generation-inference
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Hugging Face Text Generation Inference是Hugging Face公司开源的一个用于文本生成推理的 Rust、Python 和 gRPC 服务器。 Hugging Face Text Generation Inference 3.3.7及之前版本存在服务端请求伪造漏洞，该漏洞源于OpenAI兼容多模态聊天完成端点中的fetch_image函数未对私有、回环、链路本地或云元数据目标地址进行验证，且reqwest HTTP客户端默认跟随重定向，导致攻击者可通过提供特制的im

CVSS 8.6 · High EPSS 0.43% · P35

Affected Version Matrix 1

VendorProduct Version RangeStatus
huggingface text-generation-inference ≤ 3.3.7 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-63086

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
text-generation-inference 3.3.7 SSRF via fetch_image in multimodal chat completions
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
服务端请求伪造(SSRF)
Source: CVE Program / CVE List V5
Vulnerability Title
Hugging Face Text Generation Inference 服务端请求伪造漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Hugging Face Text Generation Inference是Hugging Face公司开源的一个用于文本生成推理的 Rust、Python 和 gRPC 服务器。 Hugging Face Text Generation Inference 3.3.7及之前版本存在服务端请求伪造漏洞，该漏洞源于OpenAI兼容多模态聊天完成端点中的fetch_image函数未对私有、回环、链路本地或云元数据目标地址进行验证，且reqwest HTTP客户端默认跟随重定向，导致攻击者可通过提供特制的im
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
huggingface text-generation-inference 0 ~ 3.3.7 -

II. Public POCs for CVE-2026-63086

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 6096 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-63086

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-63086 (1)

Security Blog Posts for CVE-2026-63086 (1)

IV. Related Vulnerabilities

Same vendor: huggingface
Same weakness: CWE-918

V. Comments for CVE-2026-63086

No comments yet

Leave a comment