CVE-2026-54044
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers.
Impact
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.
An attacker can exploit this over the network, with a regular user account, without any action by a user. If it succeeds: high risk of data being read. The attack can reach beyond the vulnerable component itself.
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Danny-avila | LibreChat | before 0.8.7 |
| LibreChat-AI | LibreChat | Version < 0.8.7 |
Weakness classification
References
- NVD record
- CVE.org record
- https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-qh43-24gm-5j57
- https://github.com/LibreChat-AI/LibreChat/pull/13559
- https://github.com/LibreChat-AI/LibreChat/commit/07af6ee288b1fdb610105ffbac7c1f34103a8f46
- https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.7
- https://www.librechat.ai/changelog/v0.8.7