CVE-2026-54030
Last modified
CVE-2026-54030 is a high-severity vulnerability rated 8/10 on the CVSS scale. 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. EPSS estimates a 0.11% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:N
Weakness Enumeration
References
Timeline
- Published
- Last Modified
- Status
- Undergoing Analysis
Frequently Asked Questions
What is CVE-2026-54030?
How severe is CVE-2026-54030?
How do I fix CVE-2026-54030?
Are you affected by CVE-2026-54030?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
