CVE-2026-54044

LibreChat: Shared-Agent Editor Can Exfiltrate Owner Action API Keys via OpenAPI Spec Swap

State
Published
Severity
7.7 High
Published
Nov 20, 2026
Updated
Nov 20, 2026
Reserved
Jun 11, 2026

Read the record on cve.org

Description

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.

Scores

CVSSScoreVectorSource
3.17.7 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:NGitHub_M

Weaknesses

  • CWE-522 Insufficiently Protected Credentials
  • CWE-863 Incorrect Authorization

Affected Products

ProductVersions
LibreChatLibreChat-AI
  • < 0.8.7Affected

References

Every record here comes from the CVE Program's CVE List. © 1999-2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.

© 2026 NVIDIA, the NVIDIA logo, and NVIDIA Inception are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries.