Vulnerability · Published Jul 15, 2026 · Assigned by GitHub_M

CVE-2026-61644FastGPT: /api/core/chat/record/getCollectionQuote can disclose cross-tenant dataset text due to an unbound initialId lookup

High 7.7

In plain English

A high-severity incorrect authorization in FastGPT from labring. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 24% of all known vulnerabilities).

Severity (CVSS 3.1)7.7High

Exploit odds (30 days)0.3%top 76.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

FastGPT is a knowledge-based AI application platform. From 4.14.17 until 4.15.0-beta5, the POST /api/core/chat/record/getCollectionQuote endpoint authenticates the caller's chat and collection context, but the initialId center-node lookup is not bound to that authorized context. A low-privileged tenant user can call the endpoint with valid attacker-owned appId, chatId, chatItemDataId, and collectionId values while supplying another tenant's dataset data id as initialId, causing the response to include foreign dataset quote or full-text content. This issue is fixed in version 4.15.0-beta5.

Affected products (as reported)

Vendor	Product	Versions
labring	FastGPT	>= 4.14.17, < 4.15.0-beta5

Weakness: CWE-863 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N

References

https://github.com/labring/FastGPT/security/advisories/GHSA-mmg6-2g54-j896 x_refsource_CONFIRM
https://github.com/labring/FastGPT/pull/7173 x_refsource_MISC
https://github.com/labring/FastGPT/commit/0c1840c7773c5be5d777f86228651479e02155db x_refsource_MISC
https://github.com/labring/FastGPT/releases/tag/v4.15.0-beta5 x_refsource_MISC