CVE-2026-61643 Details
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.
A vulnerability in FastGPT versions 4.14.17 prior to 4.15.0-beta5 allows authenticated users to execute private HTTP toolsets belonging to other users. This is achieved by saving a workflow node that references the victim's toolset using a crafted tool ID. While normal access routes enforce authorization and deny access to the private toolset, the workflow save and runtime paths lack the same checks. As a result, the referenced tool is executed during the workflow runtime, bypassing authorization restrictions.
Users can update to FastGPT version 4.15.0-beta5, which addresses this vulnerability by implementing the necessary authorization checks on referenced toolsets during both the workflow save and runtime execution processes.
Metrics
CVSS 4.0 Severity and Vector Strings:
VolerionCVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Jul 15, 2026CISA-ADP
Assessed Jul 20, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/labring/FastGPT/security/advisories/GHSA-93r3-wqq3-c5ch | CISA-ADP | AdvisoryExploitTechnical AnalysisVendor |
| https://github.com/labring/FastGPT/releases/tag/v4.15.0-beta5 | [email protected] | Release NotesVendor |
| https://github.com/labring/FastGPT/security/advisories/GHSA-93r3-wqq3-c5ch | [email protected] | AdvisoryExploitTechnical AnalysisVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-863 | Incorrect Authorization | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| labring FastGPT | >= 4.14.17, <= 4.14.23 (semver) 4.15.0-beta3 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jul 20, 2026 | CVE Modified | CISA-ADP |
| Jul 15, 2026 | New CVE Received | [email protected] |