CVE-2026-54031
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.8, packages/api/src/mcp/oauth/handler.ts createOAut
CVSS
6.3
Medium
EPSS
—
KEV
—
Exploit Today
—
0-100
Published: Nov 20, 2026 · Last modified: Nov 20, 2026 · CWE-918
Not enough EPSS history yet.
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.
- github.comhttps://github.com/LibreChat-AI/LibreChat/commit/4d33d8c2c71ad497fdfaa2c4334b0a2293bcbd67
- github.comhttps://github.com/LibreChat-AI/LibreChat/pull/16514
- github.comhttps://github.com/LibreChat-AI/LibreChat/releases/tag/v0.8.8
- github.comhttps://github.com/LibreChat-AI/LibreChat/security/advisories/GHSA-f7xq-83jc-cgrj
- www.librechat.aihttps://www.librechat.ai/changelog/v0.8.8