CVE-2026-54044
High 7.7No known exploitationFix status unknownTitle not yet published
Record last updated
CVSS score
High on a 0 to 10 scale
EPSS, chance of exploitation in 30 days
No EPSS score available
CISA remediation deadline
Not in the KEV catalog
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.
Weakness: CWE-522, CWE-863
Patching and mitigation
- Patch status
- Unknown: no source documents a fix
- Mitigation
- None documented
- Vendor guidance
- No vendor link on record
Affected products
No affected products documented yet.
Timeline
- No dated events documented yet.
Vendor guidance and references
- https://github.com/LibreChat-AI/LibreChat/commit/07af6ee288b1fdb610105ffbac7c1f34103a8f46 (opens in a new tab)
- https://github.com/LibreChat-AI/LibreChat/pull/13559 (opens in a new tab)
- https://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.7 (opens in a new tab)
- https://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-qh43-24gm-5j57 (opens in a new tab)
- https://www.librechat.ai/changelog/v0.8.7 (opens in a new tab)