CVE Professor
›
Back
CVE-2026-54031

CVE-2026-54031 — CWE-918

MEDIUM CVSS 6.3 NVD

CVE-2026-54031 is a MEDIUM severity Server-Side Request Forgery (SSRF) vulnerability (CWE-918) (CVSS 6.3/10) affecting affected software system. Technical vector analysis shows that an attacker can exploit this flaw remotely over the network with low-privileged access (PR:L) with zero user interaction (UI:N), triggering a scope change (S:C) across connected components and allowing unauthorized disclosure of sensitive data (C:H).

📄 Official NVD / MITRE Original Record Text

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.

Published 20.11.2026
ISO Date 2026-11-20
CVSS Version v3.1
Source NVD
CVSS v3.1 Vector Metrics
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
Attack Vector Network AV:N
Attack Complexity High AC:H
Privileges Req. Low PR:L
User Interaction None UI:N
Scope Changed S:C
Confidentiality High C:H
Integrity None I:N
Availability None A:N
AI Security Analysis & Remediation
🤖 Generating Deep AI Security Analysis…
Analyzing CVSS vector & CWE weakness structure…

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-54031
CVSS 6.3/10 · MEDIUM · 20.11.2026
CWE: CWE-918
Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:N/A:N
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 WHAT IS THIS VULNERABILITY?
Summary: 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…

⚡ ATTACK CHAIN
Remotely over internet | low-privilege account | no user interaction.
⚠️ Scope changes — impact can spread.

🌍 REAL WORLD IMPACT
All confidential data readable/stealable; pivot to other systems possible.

🛡️ REMEDIATION
→ Apply the vendor-released patch immediately.
→ Add WAF rule, create IDS alert for anomalous traffic.

⚠️ URGENCY
📋 Routine update cycle (30 days)

────────────────────────────────────────
[Kural Tabanlı Otomatik Güvenlik Analizi]

Target Reconnaissance Queries (FOFA & Shodan)
CVSS Score
6.3 / 10 · CVSS MEDIUM
Weakness Types (CWE)
CWE-918
Related CVEs
7.2
CVE-2026-129029
Server-Side Request Forgery (SSRF) vulnerability in Brainstorm Force OttoKit suretriggers allows Server Side R
7.2
CVE-2026-55372
NukeViet CMS is a multi Content Management System. Prior to 4.5.09, an unauthenticated attacker can submit the
7.2
CVE-2026-94561
NukeViet CMS is a multi Content Management System. In 4.6.00, an unauthenticated attacker can place the config
7.1
CVE-2026-132663
In Postgres Enterprise Manager (PEM), webhook URLs are not validated, and the PEM agent does not restrict the
6.3
CVE-2026-133706
request-filtering-agent before 3.2.2 contains a server-side request forgery filter bypass because address vali
5.9
CVE-2026-133505
When message history is serialized and loaded again, a tool result that contains a JSON object in the serializ