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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
Low
Basic privileges needed
User Interaction
Required
User action required
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
Low
Partial data modification
Availability
None
No disruption
CVSS Vector v3.1
Weakness Type (CWE)
Vulnerable Products 4
| Configuration | From (including) | Up to (excluding) |
|---|---|---|
|
Librechat Librechat
cpe:2.3:a:librechat:librechat:0.8.2:-:*:*:*:*:*:*
|
— | — |
|
Librechat Librechat
cpe:2.3:a:librechat:librechat:0.8.2:rc1:*:*:*:*:*:*
|
— | — |
|
Librechat Librechat
cpe:2.3:a:librechat:librechat:0.8.2:rc2:*:*:*:*:*:*
|
— | — |
|
Librechat Librechat
cpe:2.3:a:librechat:librechat:0.8.2:rc3:*:*:*:*:*:*
|
— | — |