Auth bypass in Librechat-Ai Librechat
CVE-2026-54044
- CVSS v3
- 7.7 High
- Public exploits
- None known
- EPSS
- Not scored yet
- Published
- 2026-11-20
What to do
- Fixed in
0.8.7- Affected
- 1 affected product
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/agents/actions/:agent_id in api/server/routes/agents/actions.js loads an existing action with owner credentials and merges editor-controlled metadata.domain and metadata.raw_spec while preserving metadata.api_key and related OAuth client secrets. A collaborator with EDIT permission can repoint an action to an attacker-controlled host, and a later tool invocation decrypts and sends the retained owner credential to that destination. This issue is fixed in version 0.8.7.
Published .
CVSS v3 metric
CVSS v3 base score 7.7 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N.
- Attack Vector
- Network
AV:N - Attack Complexity
- Low
AC:L - Privileges Required
- Low
PR:L - User Interaction
- None
UI:N - Scope
- Changed
S:C - Confidentiality
- High
C:H - Integrity
- None
I:N - Availability
- None
A:N
EPSS exploit prediction
FIRST.org has not scored this CVE yet. About EPSS.
Affected products
- Librechat-Ai Librechat — versions < 0.8.7