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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-61643— FastGPT: workflow runtime can execute another user's private HTTP toolset

Quick assessment

Affected
labring FastGPT
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.

labring FastGPT是labring公司开源的一款基于大语言模型的开源知识库问答系统。 labring FastGPT 4.14.17版本至4.15.0-beta5之前版本存在授权问题漏洞，该漏洞源于授权检查不当，可能导致已认证用户通过特制工具ID保存指向其他用户私有HTTP工具集的工作流节点，从而利用/api/v2/chat/completions接口解析引用并执行受害者的HTTP工具。

CVSS 5.9 · Medium EPSS 0.25% · P15

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application

Affected Version Matrix 1

VendorProduct Version RangeStatus
labring FastGPT >= 4.14.17, < 4.15.0-beta5 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-61643

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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
FastGPT: workflow runtime can execute another user's private HTTP toolset
Source: CVE Program / CVE List V5
Vulnerability Description
FastGPT is a knowledge-based AI application platform. From 4.14.17 until 4.15.0-beta5, an authenticated FastGPT user can save a workflow node that points to another user's private HTTP toolset by using a crafted saved tool id such as http-<victim_toolset_app_id>/<tool_name>. The normal toolset routes deny access, but the workflow save and runtime path did not apply the same authorization check to the referenced toolset, allowing /api/v2/chat/completions to resolve the saved reference and execute the victim-owned HTTP tool. This issue is fixed in version 4.15.0-beta5.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:H/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
授权机制不正确
Source: CVE Program / CVE List V5
Vulnerability Title
labring FastGPT 授权问题漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
labring FastGPT是labring公司开源的一款基于大语言模型的开源知识库问答系统。 labring FastGPT 4.14.17版本至4.15.0-beta5之前版本存在授权问题漏洞，该漏洞源于授权检查不当，可能导致已认证用户通过特制工具ID保存指向其他用户私有HTTP工具集的工作流节点，从而利用/api/v2/chat/completions接口解析引用并执行受害者的HTTP工具。
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
labring FastGPT >= 4.14.17, < 4.15.0-beta5 -

II. Public POCs for CVE-2026-61643

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-61643

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-61643 (1)

Vendor Pages for CVE-2026-61643 (1)

Same Patch Batch · labring · 2026-07-15 · 5 CVEs total

CVE-2026-61644 7.7 HIGH FastGPT: /api/core/chat/record/getCollectionQuote can disclose cross-tenant dataset text d
CVE-2026-61684 FastGPT: Unauthenticated cross-tenant data access via forgeable plugin-invoke JWT (default
CVE-2026-61646 FastGPT: Shared axios SSRF guard validates only the initial URL before following redirects
CVE-2026-50562 FastGPT: Untrusted PR artifacts are pushed and deployed by privileged preview workflows

IV. Related Vulnerabilities

Same product: FastGPT
Same vendor: labring
Same weakness: CWE-863

V. Comments for CVE-2026-61643

No comments yet

Leave a comment