CVE-2026-61643
MEDIUMFastGPT: workflow runtime can execute another user's private HTTP toolset
Title source: cnaDescription
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.
References (2)
Core 2
Core References
X_Refsource_Confirm x_refsource_confirm
https://github.com/labring/FastGPT/security/advisories/GHSA-93r3-wqq3-c5ch
X_Refsource_Misc x_refsource_misc
https://github.com/labring/FastGPT/releases/tag/v4.15.0-beta5
Scores
CVSS v3
5.9
EPSS
0.0015
EPSS Percentile
5.1%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:H/A:N
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
partial
Details
CWE
CWE-863
Status
published
Products (1)
labring/FastGPT
>= 4.14.17, < 4.15.0-beta5
Published
Jul 15, 2026
Tracked Since
Jul 15, 2026