CVE-2026-54031mediumCWE-918

CVE-2026-54031: medium-severity vulnerability in LibreChat-AI LibreChat

LibreChat: MCP OAuth requests can follow redirects to internal URLs after SSRF validation

Published

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

13Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 6.3epss 0.3%
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.8, packages/api/src/mcp/oauth/handler.ts createOAuthFetch validates only the initial destination for MCP OAuth discovery, registration, token, refresh, and revocation requests, then uses redirect-following fetch behavior without validating each redirect target. An attacker who can initiate MCP OAuth against a controlled endpoint can redirect server requests to internal or private addresses, reaching services that the initial SSRF checks should block. The separate MCP transport path already validates redirects and is not affected. This issue is fixed in version 0.8.8.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Affected products
LibreChat-AI · LibreChat