Vulnerability · Published Jul 7, 2026 · Assigned by GitHub_M

CVE-2026-54602FastGPT: Cross-team LLM request/response disclosure (IDOR) via /api/core/ai/record/getRecord

High 7.1

In plain English

A high-severity authorization bypass via user-controlled key in FastGPT from labring. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 30% of all known vulnerabilities).

Severity (CVSS 4.0)7.1High

Exploit odds (30 days)0.4%top 69.6% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

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.

Affected products (as reported)

Vendor	Product	Versions
labring	FastGPT	< 4.15.0

Weakness: CWE-639 · Vector: 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

References

https://github.com/labring/FastGPT/security/advisories/GHSA-6vx6-f72r-74cg x_refsource_CONFIRM
https://github.com/labring/FastGPT/commit/60c62b7af8269c826885b541bb56e6e5c424c11a x_refsource_MISC