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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-85668— Xinference 3.3.0 Unauthenticated Arbitrary-Path File Read via /v1/models/llm/auto-register

Quick assessment

Affected
xorbitsai inference
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Xorbits Inference是Xorbits团队开源的一个功能强大且用途广泛的库，专为语言、语音识别和多模态模型而设计。 Xorbits Inference 3.3.0及之前版本存在输入验证错误漏洞，该漏洞源于POST /v1/models/llm/auto-register端点接受调用者提供的model_path参数，且未进行身份验证或路径限制，导致未经身份验证的攻击者可以读取并解析服务器上任意路径下的config.json、tokenizer_config.json和chat_template.

CVSS 7.5 · High EPSS 0.61% · P49

Affected Version Matrix 1

VendorProduct Version RangeStatus
xorbitsai inference ≤ 3.3.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-85668

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
Xinference 3.3.0 Unauthenticated Arbitrary-Path File Read via /v1/models/llm/auto-register
Source: CVE Program / CVE List V5
Vulnerability Description
Xinference (affected commit 4a94832, v3.x) contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint, which accepts a caller-supplied model_path parameter without authentication or path confinement. The endpoint reads and parses config.json, tokenizer_config.json, and chat_template.jinja files at the supplied path and reflects the parsed content back to the caller, allowing an unauthenticated attacker to probe the server filesystem and extract content of files with those names in any directory.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
文件名或路径的外部可控制
Source: CVE Program / CVE List V5
Vulnerability Title
Xorbits Inference 输入验证错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Xorbits Inference是Xorbits团队开源的一个功能强大且用途广泛的库，专为语言、语音识别和多模态模型而设计。 Xorbits Inference 3.3.0及之前版本存在输入验证错误漏洞，该漏洞源于POST /v1/models/llm/auto-register端点接受调用者提供的model_path参数，且未进行身份验证或路径限制，导致未经身份验证的攻击者可以读取并解析服务器上任意路径下的config.json、tokenizer_config.json和chat_template.
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
xorbitsai inference 0 ~ 3.3.0 -

II. Public POCs for CVE-2026-85668

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-85668

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-85668 (1)

Other References for CVE-2026-85668 (2)

IV. Related Vulnerabilities

Same product: inference
Same vendor: xorbitsai
Same weakness: CWE-73