LibreChat Exfiltrates Server Secrets via MCP Server URL Injection_CVE-2026-32625

{
    "lastseen": "",
    "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.",
    "published": "2026-06-02T22:35:00.859Z",
    "modified": "2026-06-02T22:35:00.859Z",
    "type": "cve",
    "title": "LibreChat Exfiltrates Server Secrets via MCP Server URL Injection",
    "source": "GitHub_M",
    "references": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx",
    "id": "CVE-2026-32625",
    "bulletinFamily": "",
    "cwe": [
        "CWE-200"
    ],
    "cvelist": null,
    "sourceData": "danny-avila LibreChat < 0.8.4-rc1",
    "sourceHref": "",
    "cvss": {
        "score": 9.6,
        "severity": "CRITICAL",
        "vector": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N",
        "version": "3.1"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "",
    "category_name": "CVE",
    "post_link": "",
    "product": "LibreChat",
    "version": "< 0.8.4-rc1",
    "vendor": "danny-avila",
    "ai_description": "LibreChat server compromise via MCP server URL injection, exposing sensitive credentials and database information",
    "ai_severity": "Critical",
    "ai_vendor": "danny-avila",
    "ai_product": "LibreChat",
    "ai_version": "< 0.8.4-rc1",
    "ai_score": 9.6
}