Auth bypass in Danny-Avila Librechat
CVE-2026-31944
LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim’s OAuth tokens are stored on the attacker’s LibreChat account, enabling account takeover of the victim’s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1.
Vulnerability class: Broken Authentication
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.6 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N.
EPSS exploit prediction
EPSS 0.003, 22.0th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Danny-Avila Librechat — versions >= v0.8.2, <= 0.8.2-rc3
- Librechat — versions 0.8.2
Weakness classification (CWE)
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g (Exploit, Vendor Advisory)