7.6 HIGH
- CVSS version: 3.1
- Attack vector (AV): NETWORK
- Attack complexity (AC): LOW
- Privileges required (PR): LOW
- User interaction (UI): REQUIRED
- Scope (S): CHANGED
- Confidentiality impact (C): HIGH
- Integrity impact (I): LOW
- Availability impact (A): NONE
by @LeSuisse Activity log
- Created automatic suggestion
- @LeSuisse accepted
- @LeSuisse published on GitHub
LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link
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.
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g x_refsource_CONFIRM
Affected products
- ==>= v0.8.2, <= 0.8.2-rc3
Package maintainers
-
@niklaskorz Niklas Korz <nixpkgs@korz.dev>