MEDIUMCVSS v3.1 6.3Vulnerability

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 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.

Properties

Severity
MEDIUM
Nvd fetched at
2026-11-22T12:30:49.958423+00:00
Epss score
0.00347
Cvss score
6.3
Cvss severity
MEDIUM
Retrieved at
2026-11-22T12:32:27+00:00
Score
6.3
Last source
FIRST EPSS
Cvss version
3.1
Cve id
CVE-2026-54031
Cvss vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
First seen by Signal
2026-11-20T23:48:22+00:00
Name
CVE-2026-54031
Vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Published at
2026-11-20T20:17:41.713
Last modified
2026-11-20T20:17:41.713
Epss percentile
0.2887

Related Entities (1)

HAS_WEAKNESS (1)

Related research

Explore deeper with Ninja Signal's threat intelligence graph

CVE-2026-54031 (CVSS v3.1 6.3) — Ninja Signal Threat Intelligence | Ninja Signal