CVE-2026-54602
HIGHFastGPT: Cross-team LLM request/response disclosure (IDOR) via /api/core/ai/record/getRecord
Title source: cnaDescription
FastGPT is a knowledge-based AI application platform. Prior to 4.15.0, GET /api/core/ai/record/getRecord authenticates the caller but loads LLM request and response traces only by requestId without team scoping, allowing any authenticated user to read another team's prompts, retrieved RAG chunks, and completions if the requestId is known. This issue is fixed in version 4.15.0.
References (2)
Core 2
Core References
X_Refsource_Confirm x_refsource_confirm
https://github.com/labring/FastGPT/security/advisories/GHSA-6vx6-f72r-74cg
X_Refsource_Misc x_refsource_misc
https://github.com/labring/FastGPT/commit/60c62b7af8269c826885b541bb56e6e5c424c11a
Scores
CVSS v4
7.1
EPSS
0.0023
EPSS Percentile
13.4%
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CISA SSVC
Vulnrichment
Exploitation
none
Automatable
no
Technical Impact
partial
Details
CWE
CWE-639
Status
published
Products (1)
labring/FastGPT
< 4.15.0
Published
Jul 07, 2026
Tracked Since
Jul 08, 2026