CVE-2026-32625: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in danny-avila LibreChat
CVE-2026-32625 is a critical vulnerability in LibreChat versions up to 0. 8. 3 where authenticated users can exploit environment variable interpolation in MCP server URLs to exfiltrate sensitive secrets. By crafting a malicious MCP server configuration URL containing environment variable references, an attacker can cause the server to send critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI to an attacker-controlled domain. This leads to full compromise of cryptographic materials and database credentials without needing administrative privileges. The issue is patched in version 0. 8. 4-rc1.
AI Analysis
Technical Summary
LibreChat's Model Context Protocol (MCP) server integration performs environment variable interpolation on user-supplied MCP server URLs during Zod schema validation. In versions prior to 0.8.4-rc1, any authenticated user can create a malicious MCP server configuration URL that includes references to environment variables. When the server resolves these placeholders, it connects to the attacker-controlled domain and transmits sensitive environment variables including cryptographic keys and database credentials. This vulnerability allows unauthorized exposure of sensitive information (CWE-200) and can lead to full compromise of the installation's secrets and database access. The vulnerability has a CVSS 3.1 score of 9.6 (critical) and is fixed in version 0.8.4-rc1.
Potential Impact
An attacker with authenticated user privileges can exfiltrate critical secrets such as cryptographic keys (CREDS_KEY, CREDS_IV), JWT secret, and database connection strings (MONGO_URI) by exploiting environment variable interpolation in MCP server URLs. This results in full compromise of the affected LibreChat installation's cryptographic materials and database credentials, enabling potential further unauthorized access and data breaches. No administrative privileges are required to exploit this vulnerability.
Mitigation Recommendations
Upgrade LibreChat to version 0.8.4-rc1 or later, where this vulnerability is patched. Until the upgrade is applied, restrict authenticated user capabilities to prevent creation or modification of MCP server configurations containing environment variable references. Patch status is confirmed by the vendor's versioning information indicating the fix in 0.8.4-rc1.
CVE-2026-32625: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in danny-avila LibreChat
Description
CVE-2026-32625 is a critical vulnerability in LibreChat versions up to 0. 8. 3 where authenticated users can exploit environment variable interpolation in MCP server URLs to exfiltrate sensitive secrets. By crafting a malicious MCP server configuration URL containing environment variable references, an attacker can cause the server to send critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI to an attacker-controlled domain. This leads to full compromise of cryptographic materials and database credentials without needing administrative privileges. The issue is patched in version 0. 8. 4-rc1.
CVSS v3.1
Score 9.6critical
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
LibreChat's Model Context Protocol (MCP) server integration performs environment variable interpolation on user-supplied MCP server URLs during Zod schema validation. In versions prior to 0.8.4-rc1, any authenticated user can create a malicious MCP server configuration URL that includes references to environment variables. When the server resolves these placeholders, it connects to the attacker-controlled domain and transmits sensitive environment variables including cryptographic keys and database credentials. This vulnerability allows unauthorized exposure of sensitive information (CWE-200) and can lead to full compromise of the installation's secrets and database access. The vulnerability has a CVSS 3.1 score of 9.6 (critical) and is fixed in version 0.8.4-rc1.
Potential Impact
An attacker with authenticated user privileges can exfiltrate critical secrets such as cryptographic keys (CREDS_KEY, CREDS_IV), JWT secret, and database connection strings (MONGO_URI) by exploiting environment variable interpolation in MCP server URLs. This results in full compromise of the affected LibreChat installation's cryptographic materials and database credentials, enabling potential further unauthorized access and data breaches. No administrative privileges are required to exploit this vulnerability.
Mitigation Recommendations
Upgrade LibreChat to version 0.8.4-rc1 or later, where this vulnerability is patched. Until the upgrade is applied, restrict authenticated user capabilities to prevent creation or modification of MCP server configurations containing environment variable references. Patch status is confirmed by the vendor's versioning information indicating the fix in 0.8.4-rc1.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-03-12T15:29:36.558Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a1f64cce29bf47b5010d68d
Added to database: 6/2/2026, 11:18:36 PM
Last enriched: 6/2/2026, 11:33:37 PM
Last updated: 6/3/2026, 1:25:17 AM
Views: 10
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.