CVE-2026-32625: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in danny-avila LibreChat
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.
AI Analysis
Technical Summary
In LibreChat versions up to and including 0.8.3, the MCP server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. This allows any authenticated user to craft a malicious MCP server configuration with a URL referencing environment variables. When the server connects to this URL, it transmits sensitive secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL, exposing critical cryptographic materials and database credentials. This vulnerability is tracked as CVE-2026-32625 and is fixed in version 0.8.4-rc1.
Potential Impact
The vulnerability exposes highly sensitive environment variables containing cryptographic keys and database credentials to unauthorized actors. This can lead to full compromise of the LibreChat installation's cryptographic materials and database access. The attack requires only authenticated user privileges, significantly lowering the barrier for exploitation. There is no indication of denial of service or integrity impact, but confidentiality is severely affected.
Mitigation Recommendations
Upgrade LibreChat to version 0.8.4-rc1 or later, where this vulnerability is patched. Until upgrading, restrict authenticated user capabilities to prevent creation of malicious MCP server configurations. Patch status is not explicitly stated as 'official-fix' in the vendor advisory, but the description confirms the issue is fixed in 0.8.4-rc1. Monitor vendor advisories for any additional updates.
CVE-2026-32625: CWE-200: Exposure of Sensitive Information to an Unauthorized Actor in danny-avila LibreChat
Description
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.
CVSS v3.1
Score 9.6critical
Affected software
pkg:github/danny-avila/LibreChatRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
In LibreChat versions up to and including 0.8.3, the MCP server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. This allows any authenticated user to craft a malicious MCP server configuration with a URL referencing environment variables. When the server connects to this URL, it transmits sensitive secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL, exposing critical cryptographic materials and database credentials. This vulnerability is tracked as CVE-2026-32625 and is fixed in version 0.8.4-rc1.
Potential Impact
The vulnerability exposes highly sensitive environment variables containing cryptographic keys and database credentials to unauthorized actors. This can lead to full compromise of the LibreChat installation's cryptographic materials and database access. The attack requires only authenticated user privileges, significantly lowering the barrier for exploitation. There is no indication of denial of service or integrity impact, but confidentiality is severely affected.
Mitigation Recommendations
Upgrade LibreChat to version 0.8.4-rc1 or later, where this vulnerability is patched. Until upgrading, restrict authenticated user capabilities to prevent creation of malicious MCP server configurations. Patch status is not explicitly stated as 'official-fix' in the vendor advisory, but the description confirms the issue is fixed in 0.8.4-rc1. Monitor vendor advisories for any additional updates.
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: 06/02/2026, 23:18:36 UTC
Last enriched: 06/10/2026, 11:09:11 UTC
Last updated: 07/18/2026, 17:31:43 UTC
Views: 134
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.