CVE-2026-44654 LibreChat: Shared-agent editor can globally delete owner's file records — breaks owner's other private agents

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, a shared-agent editor can delete file records through DELETE /api/files that the owner has reused across multiple agents. The deletion removes the file globally — not just from the...

CVE-2026-44653 LibreChat Shared MCP Server View Leaks Decrypted Admin Secrets

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

EUVD-2026-34047

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

CVE-2026-44653 LibreChat Shared MCP Server View Leaks Decrypted Admin Secrets

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

CVE-2026-32625

LibreChat vulnerability CVE-2026-32625 affects versions up to 0.8.3 where MCP server URL validation expands ${VAR} against process.env during Zod schema checks. An authenticated user can configure a malicious MCP URL to exfiltrate secrets (CREDS_KEY, CREDS_IV, JWT_SECRET, MONGO_URI) to an attacke...

CVE-2026-32625 LibreChat Exfiltrates Server Secrets via MCP Server URL Injection

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...

CVE-2026-32625

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...

CVE-2026-31942 LibreChat has IDOR in API Keys Management that allows any authenticated user to overwrite other users' API keys

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.7.6, an Insecure Direct Object Reference IDOR vulnerability exists in the API keys management endpoint PUT /api/keys. Due to the use of the JavaScript object spread operator after setting...

CVE-2026-31942 LibreChat has IDOR in API Keys Management that allows any authenticated user to overwrite other users' API keys

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.7.6, an Insecure Direct Object Reference IDOR vulnerability exists in the API keys management endpoint PUT /api/keys. Due to the use of the JavaScript object spread operator after setting...

CVE-2026-31942

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.7.6, an Insecure Direct Object Reference IDOR vulnerability exists in the API keys management endpoint PUT /api/keys. Due to the use of the JavaScript object spread operator after setting...

CVE-2026-31942

LibreChat (up to version 0.7.6) is affected by an Insecure Direct Object Reference (IDOR) in the API keys management endpoint (PUT /api/keys). After setting the authenticated user’s ID, an attacker can inject a userId parameter in the request body to overwrite other users’ API keys (e.g., OpenAI,...

CVE-2026-31942 LibreChat has IDOR in API Keys Management that allows any authenticated user to overwrite other users' API keys

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.7.6, an Insecure Direct Object Reference IDOR vulnerability exists in the API keys management endpoint PUT /api/keys. Due to the use of the JavaScript object spread operator after setting...

LibreChat 安全漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within one interface. LibreChat versions 0.8.3 and earlier have a security vulnerability caused by improper access control to the MCP...

CVE-2026-31942: Missing Authorization

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.7.6, an Insecure Direct Object Reference IDOR vulnerability exists in the API keys management endpoint PUT /api/keys. Due to the use of the JavaScript object spread operator after setting...

CVE-2026-44654: Incorrect Authorization

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, a shared-agent editor can delete file records through DELETE /api/files that the owner has reused across multiple agents. The deletion removes the file globally — not just from the...

LibreChat 信息泄露漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within a single interface. Versions of LibreChat 0.8.3 and earlier contained a security vulnerability known as information leakage. Th...

CVE-2026-32625: Exposure of Sensitive Information to an Unauthorized Actor

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...

LibreChat 安全漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within a single interface. LibreChat versions 0.7.6 and earlier contain security vulnerabilities. These vulnerabilities stem from...

CVE-2026-44653: Insertion of Sensitive Information Into Sent Data

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only VIEW access to an MCP server can retrieve the server's decrypted admin-managed secrets through GET /api/mcp/servers and GET /api/mcp/servers/:serverName. The returned...

LibreChat 安全漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within one interface. LibreChat versions 0.8.3 and earlier have a security vulnerability caused by a file deletion permission issue...