Description
LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by uploading new files to the file context or file search, even if they have no permissions for this agent. This issue is fixed in version 0.8.2-rc2.
Affected products
librechat: librechat
References8
- github.com/danny-avila/LibreChat/security/advisories/GHSA-xcmf-… ExploitVendor Advisory
- github.com/danny-avila/LibreChat/commit/4b9c6ab1cb9de626736de70… Patch
- cwe.mitre.org/data/definitions/284.html Not Applicable
- cwe.mitre.org/data/definitions/862.html Not Applicable
- github.com/danny-avila/LibreChat/releases/tag/v0.8.2-rc2 Release Notes
- owasp.org/Top10/A01_2021-Broken_Access_Control Not Applicable
- owasp.org/www-project-web-security-testing-guide/v42/4-Web_Appl… Technical Description
- raw.githubusercontent.com/OWASP/ASVS/v5.0.0/5.0/OWASP_Applicati… Technical Description
Metrics
- CVSS 3.1
-
5.9
MEDIUM
Score source: NVD
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:N - EPSS — exploit probability
- 0% percentile: 27 · as of 11 November 2026
- CWE
- CWE-284CWE-862
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.