CVEvulnerability
CVE-2026-54030
9.3 CRITICAL
Official page ↗
- Status
- Analyzed
- Published
- 2026-06-25
- Last modified
- 2026-10-25
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 8.0 HIGH — CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:N
- CVSS 3.1 ([email protected])
- 9.3 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:N
- Weaknesses
- CWE-346
Description
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a malicious MCP server to steal access tokens intended for a legitimate server. This vulnerability is fixed in 0.8.5.
Affected configurations
• librechat librechat (<= 0.8.4)
• librechat librechat 0.8.5
Related
Weakness · CWE (1)
- CWE-346 Origin Validation Error weakness
References
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 Exploit, Vendor Advisory
- https://github.com/danny-avila/LibreChat/security/advisories/GHSA-gvpj-vm2f-2m23 Exploit, Vendor Advisory