CVE-2026-54044
7.7HighPublished 20 Nov 2026 · NVD status: Received
7.7CVSS
High
0CVSS v3.110
- Attack vector
- Network
- Complexity
- Low
- Privileges
- Low
- User action
- None
- Impact
- High impact on confidentiality
- Weakness
- CWE-522, CWE-863
✓ NVD record loaded
› AI triage queued▋
CVSS v3.1 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
NVD 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.
References
- https://github.com/LibreChat-AI/LibreChat/commit/07af6ee288b1fdb610105ffbac7c1f34103a8f46
- https://github.com/LibreChat-AI/LibreChat/pull/13559
- https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.7
- https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-qh43-24gm-5j57
- https://www.librechat.ai/changelog/v0.8.7