LibreChat is an enhanced ChatGPT clone that supports multiple AI providers.
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.
Read at NIST National Vulnerability Database (CVE API 2.0)
- Vendor
- LibreChat-AI
- Product
- LibreChat
- CVSS v3.1
- 7.7 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- Fix
- available
- Weakness
- CWE-522, CWE-863
- Exposure class
- AI infrastructure
- NVD status
- Received
Why it ranks 35 (Notable)
- CVSS v3.1 7.7 high
- Product class: AI infrastructure
- Fix available
- Recency: items published within 24 hours gain 15, within 72 hours 6, within 7 days 2.
Links
- NIST National Vulnerability Database (CVE API 2.0) (nvd.nist.gov)
- CVE-2026-54044 on this site · NVD · CVE.org · Vulnpedia
Related coverage
Other items that share a CVE or were clustered with this one.