Vendor CVEs
Librechat
All CVEs
64 total · sorted by risk| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2025-69222 | Cri | 0.60 | 9.1 | 0.05 | Jan 7, 2026 | LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 is prone to a server-side request forgery (SSRF) vulnerability due to missing restrictions of the Actions feature in the default configuration. LibreChat enables users to configure agents with predefined… | ||
| CVE-2025-8850 | Hig | 0.57 | 8.8 | 0.00 | Oct 30, 2025 | In danny-avila/librechat version 0.7.9, there is an insecure API design issue in the 2-Factor Authentication (2FA) flow. The system allows users to disable 2FA without requiring a valid OTP or backup code, bypassing the intended verification process. This vulnerability occurs… | ||
| CVE-2024-11170 | Hig | 0.57 | 8.8 | 0.02 | Mar 20, 2025 | A vulnerability in danny-avila/librechat version git 81f2936 allows for path traversal due to improper sanitization of file paths by the multer middleware. This can lead to arbitrary file write and potentially remote code execution. The issue is fixed in version 0.7.6. | ||
| CVE-2026-32625 | Cri | 0.56 | 9.6 | 0.03 | Jun 2, 2026 | 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… | ||
| CVE-2025-66201 | Hig | 0.53 | 8.1 | 0.00 | Nov 29, 2025 | LibreChat is a ChatGPT clone with additional features. Prior to version 0.8.1-rc2, LibreChat is vulnerable to Server-side Request Forgery (SSRF), by passing specially crafted OpenAPI specs to its "Actions" feature and making the LLM use those actions. It could be used by an… | ||
| CVE-2025-41258 | Hig | 0.52 | 8.0 | 0.00 | Mar 18, 2026 | LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API. | ||
| CVE-2026-4276 | Hig | 0.49 | 7.5 | 0.00 | Mar 16, 2026 | LibreChat RAG API, version 0.7.0, contains a log-injection vulnerability that allows attackers to forge log entries. | ||
| CVE-2025-8849 | Hig | 0.49 | 7.5 | 0.00 | Oct 31, 2025 | LibreChat version 0.7.9 is vulnerable to a Denial of Service (DoS) attack due to unbounded parameter values in the `/api/memories` endpoint. The `key` and `value` parameters accept arbitrarily large inputs without proper validation, leading to a null pointer error in the… | ||
| CVE-2025-7104 | Hig | 0.49 | 7.5 | 0.00 | Sep 29, 2025 | A mass assignment vulnerability exists in danny-avila/librechat, affecting all versions. This vulnerability allows attackers to manipulate sensitive fields by automatically binding user-provided data to internal object properties or database fields without proper filtering. As a… | ||
| CVE-2024-11171 | Hig | 0.49 | 7.5 | 0.01 | Mar 20, 2025 | In danny-avila/librechat version git 0c2a583, there is an improper input validation vulnerability. The application uses multer middleware for handling multipart file uploads. When using in-memory storage (the default setting for multer), there is no limit on the upload file… | ||
| CVE-2026-31943 | Hig | 0.48 | 8.5 | 0.00 | Mar 27, 2026 | LibreChat is a ChatGPT clone with additional features. Prior to version 0.8.3, `isPrivateIP()` in `packages/api/src/auth/domain.ts` fails to detect IPv4-mapped IPv6 addresses in their hex-normalized form, allowing any authenticated user to bypass SSRF protection and make the… | ||
| CVE-2026-54039 | Hig | 0.46 | 8.1 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. From 0.7.0 until 0.8.6, when local registration is enabled and at least one social provider is configured, POST /api/auth/register passes an unparsed request object into… | ||
| CVE-2026-44654 | Hig | 0.46 | 8.1 | 0.00 | Jun 2, 2026 | 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… | ||
| CVE-2025-69220 | Hig | 0.46 | 7.1 | 0.00 | Jan 7, 2026 | LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by… | ||
| CVE-2026-54030 | Hig | 0.45 | 8.0 | 0.00 | Jun 25, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a… | ||
| CVE-2026-54044 | Hig | 0.43 | 7.7 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/agents/actions/:agent_id in api/server/routes/agents/actions.js loads an existing action with owner credentials and merges editor-controlled metadata.domain and… | ||
| CVE-2026-31945 | Hig | 0.43 | 7.7 | 0.00 | Mar 27, 2026 | LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisor… | ||
| CVE-2026-31944 | Hig | 0.42 | 7.6 | 0.00 | Mar 13, 2026 | LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the… | ||
| CVE-2025-66451 | Med | 0.42 | 6.5 | 0.00 | Dec 11, 2025 | LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups (/api/prompts/groups/:groupId). However, the request bodies are not… | ||
| CVE-2024-11173 | Med | 0.42 | 6.5 | 0.01 | Mar 20, 2025 | An unhandled exception in the danny-avila/librechat repository, version git 600d217, can cause the server to crash, leading to a full denial of service. This issue occurs when certain API endpoints receive malformed input, resulting in an uncaught exception. Although a valid JWT… | ||
| CVE-2024-10366 | Med | 0.42 | 6.5 | 0.00 | Mar 20, 2025 | An improper access control vulnerability (IDOR) exists in the delete attachments functionality of danny-avila/librechat version v0.7.5-rc2. The endpoint does not verify whether the provided attachment ID belongs to the current user, allowing any authenticated user to delete… | ||
| CVE-2026-33265 | Med | 0.41 | 6.3 | 0.00 | Mar 18, 2026 | In LibreChat 0.8.1-rc2, a logged-in user obtains a JWT for both the LibreChat API and the RAG API. | ||
| CVE-2025-66452 | Med | 0.40 | 6.1 | 0.00 | Dec 11, 2025 | LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, there is no handler for JSON parsing errors; SyntaxError from express.json() includes user input in the error message, which gets reflected in responses. User input (including HTML/JavaScript)… | ||
| CVE-2026-31942 | Hig | 0.39 | 7.1 | 0.00 | Jun 2, 2026 | 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… | ||
| CVE-2026-54042 | Med | 0.37 | 6.8 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/auth/2fa/verify-temp in api/server/routes/auth.js calls verify2FAWithTempToken and accepts repeated TOTP or backup-code guesses without a dedicated attempt limiter. An attacker… | ||
| CVE-2026-31951 | Med | 0.37 | 6.8 | 0.00 | Mar 27, 2026 | LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server… | ||
| CVE-2025-7105 | Med | 0.37 | 5.7 | 0.00 | Feb 2, 2026 | A vulnerability in danny-avila/librechat allows attackers to exploit the unrestricted Fork Function in `/api/convos/fork` to fork numerous contents rapidly. If the forked content includes a Mermaid graph with a large number of nodes, it can lead to a JavaScript heap out of… | ||
| CVE-2026-54038 | Med | 0.35 | 6.5 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.9, GET /api/permissions/search-principals passes the q parameter to JavaScript RegExp construction and MongoDB regex queries in packages/data-schemas/src/methods/userGroup.ts… | ||
| CVE-2026-54026 | Med | 0.35 | 6.5 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, POST /api/messages/:conversationId authorizes req.params.conversationId in api/server/middleware/validateMessageReq.js but persists attacker-controlled req.body.conversationId through… | ||
| CVE-2026-54045 | Med | 0.35 | 6.5 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/auth/requestPasswordReset calls deleteTokens by user ID before creating a reset token, while password-reset and email-verification records in… | ||
| CVE-2026-44653 | Med | 0.35 | 6.5 | 0.00 | Jun 2, 2026 | 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… | ||
| CVE-2026-31949 | Med | 0.35 | 6.5 | 0.00 | Mar 13, 2026 | LibreChat is a ChatGPT clone with additional features. Prior to 0.8.3-rc1, a Denial of Service (DoS) vulnerability exists in the DELETE /api/convos endpoint that allows an authenticated attacker to crash the Node.js server process by sending malformed requests. The DELETE… | ||
| CVE-2025-66450 | Med | 0.35 | 5.4 | 0.00 | Dec 11, 2025 | LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when a user posts a question, the iconURL parameter of the POST request can be modified by an attacker. The malicious code is then stored in the chat which can then be shared to other users. When… | ||
| CVE-2025-8848 | Med | 0.35 | 5.4 | 0.00 | Oct 22, 2025 | A vulnerability in danny-avila/librechat version 0.7.9 allows for HTML injection via the Accept-Language header. When a logged-in user sends an HTTP GET request with a crafted Accept-Language header, arbitrary HTML can be injected into the tag of the response.… | ||
| CVE-2026-54043 | Med | 0.34 | 6.3 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, packages/data-schemas/src/methods/file.ts updateFileUsage accepts chat attachment files[].file_id values without restricting the lookup to the authenticated owner. An authenticated… | ||
| CVE-2026-54031 | Med | 0.34 | 6.3 | — | Nov 20, 2026 | 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… | ||
| CVE-2026-34371 | Med | 0.34 | 6.3 | 0.00 | Apr 7, 2026 | LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the execute_code sandbox when persisting code-generated artifacts. On deployments using the default local file strategy, a malicious artifact filename containing… | ||
| CVE-2025-7106 | Med | 0.34 | 5.3 | 0.00 | Sep 23, 2025 | danny-avila/librechat is affected by an authorization bypass vulnerability due to improper access control checks. The `checkAccess` function in `api/server/middleware/roles/access.js` uses `permissions.some()` to validate permissions, which incorrectly grants access if only one… | ||
| CVE-2024-12580 | Med | 0.34 | 5.3 | 0.01 | Mar 20, 2025 | A vulnerability in danny-avila/librechat prior to version 0.7.6 allows for logs debug injection. The parameters sessionId, fileId, userId, and file_id in the /code/download/:sessionId/:fileId and /download/:userId/:file_id APIs are not validated or filtered, leading to potential… | ||
| CVE-2024-11167 | Med | 0.34 | 5.3 | 0.01 | Mar 20, 2025 | An improper access control vulnerability in danny-avila/librechat versions prior to 0.7.6 allows authenticated users to delete other users' prompts via the groupid parameter. This issue occurs because the endpoint does not verify whether the provided prompt ID belongs to the… | ||
| CVE-2026-54032 | Med | 0.33 | 6.1 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, client/src/components/Chat/Input/MCPConfigDialog.tsx renders the remote MCP details.description value through dangerouslySetInnerHTML without sanitization, allowing a malicious MCP server… | ||
| CVE-2026-54023 | Med | 0.32 | — | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. From 0.8.5 until 0.8.6, GET /api/user in api/server/controllers/UserController.js getUserController serializes federatedTokens and tokenset to the authenticated browser because an earlier… | ||
| CVE-2024-10359 | Med | 0.30 | 4.6 | 0.00 | Mar 20, 2025 | In danny-avila/librechat version v0.7.5-rc2, a vulnerability exists in the preset creation functionality where a user can manipulate the user ID field through mass assignment. This allows an attacker to inject a different user ID into the preset object, causing the preset to… | ||
| CVE-2025-69221 | Med | 0.28 | 4.3 | 0.00 | Jan 7, 2026 | LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control when querying agent permissions. An authenticated attacker can read the permissions of arbitrary agents, even if they have no permissions for this agent. LibreChat… | ||
| CVE-2026-54046 | Med | 0.27 | 5.3 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, unauthenticated POST /api/user/verify requests in api/server/routes/user.js call api/server/services/AuthService.js verifyEmail and return distinct responses for unknown, verified, and… | ||
| CVE-2026-31950 | Med | 0.27 | 5.3 | 0.00 | Mar 27, 2026 | LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc2 through 0.8.2-rc3, the SSE streaming endpoint `/api/agents/chat/stream/:streamId` does not verify that the requesting user owns the stream. Any authenticated user who obtains or guesses a valid stream… | ||
| CVE-2026-54041 | Low | 0.13 | 3.1 | — | Nov 20, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, the POST /api/auth/login local-login validation path in api/strategies/localStrategy.js logs req.body, including the submitted plaintext password, during a Zod validation failure. The… | ||
| CVE-2026-54040 | Med | 0.00 | 5.9 | 0.00 | Jun 25, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the POST /api/auth/2fa/backup/regenerate endpoint regenerates all 2FA backup codes without requiring any TOTP token or existing backup code verification. An attacker with a stolen… | ||
| CVE-2026-54037 | Med | 0.00 | 6.5 | 0.01 | Jun 25, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the fix for CVE-2025-7105 added forkIpLimiter and forkUserLimiter rate limiters to POST /api/convos/fork to prevent rapid-fire conversation duplication. However, the POST… | ||
| CVE-2026-54033 | Hig | 0.00 | 7.7 | 0.00 | Jun 25, 2026 | LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, LibreChat allows users to configure custom OpenAI-compatible API endpoints by setting a baseURL. This URL is used to construct HTTP requests without any SSRF validation — no private… |
- risk 0.60cvss 9.1epss 0.05
LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 is prone to a server-side request forgery (SSRF) vulnerability due to missing restrictions of the Actions feature in the default configuration. LibreChat enables users to configure agents with predefined…
- risk 0.57cvss 8.8epss 0.00
In danny-avila/librechat version 0.7.9, there is an insecure API design issue in the 2-Factor Authentication (2FA) flow. The system allows users to disable 2FA without requiring a valid OTP or backup code, bypassing the intended verification process. This vulnerability occurs…
- risk 0.57cvss 8.8epss 0.02
A vulnerability in danny-avila/librechat version git 81f2936 allows for path traversal due to improper sanitization of file paths by the multer middleware. This can lead to arbitrary file write and potentially remote code execution. The issue is fixed in version 0.7.6.
- risk 0.56cvss 9.6epss 0.03
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…
- risk 0.53cvss 8.1epss 0.00
LibreChat is a ChatGPT clone with additional features. Prior to version 0.8.1-rc2, LibreChat is vulnerable to Server-side Request Forgery (SSRF), by passing specially crafted OpenAPI specs to its "Actions" feature and making the LLM use those actions. It could be used by an…
- risk 0.52cvss 8.0epss 0.00
LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API.
- risk 0.49cvss 7.5epss 0.00
LibreChat RAG API, version 0.7.0, contains a log-injection vulnerability that allows attackers to forge log entries.
- risk 0.49cvss 7.5epss 0.00
LibreChat version 0.7.9 is vulnerable to a Denial of Service (DoS) attack due to unbounded parameter values in the `/api/memories` endpoint. The `key` and `value` parameters accept arbitrarily large inputs without proper validation, leading to a null pointer error in the…
- risk 0.49cvss 7.5epss 0.00
A mass assignment vulnerability exists in danny-avila/librechat, affecting all versions. This vulnerability allows attackers to manipulate sensitive fields by automatically binding user-provided data to internal object properties or database fields without proper filtering. As a…
- risk 0.49cvss 7.5epss 0.01
In danny-avila/librechat version git 0c2a583, there is an improper input validation vulnerability. The application uses multer middleware for handling multipart file uploads. When using in-memory storage (the default setting for multer), there is no limit on the upload file…
- risk 0.48cvss 8.5epss 0.00
LibreChat is a ChatGPT clone with additional features. Prior to version 0.8.3, `isPrivateIP()` in `packages/api/src/auth/domain.ts` fails to detect IPv4-mapped IPv6 addresses in their hex-normalized form, allowing any authenticated user to bypass SSRF protection and make the…
- risk 0.46cvss 8.1epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. From 0.7.0 until 0.8.6, when local registration is enabled and at least one social provider is configured, POST /api/auth/register passes an unparsed request object into…
- risk 0.46cvss 8.1epss 0.00
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…
- risk 0.46cvss 7.1epss 0.00
LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior of arbitrary agents by…
- risk 0.45cvss 8.0epss 0.00
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.5, LibreChat's MCP OAuth implementation does not validate that the resource parameter from OAuth Protected Resource metadata (RFC 9728) matches the configured MCP server URL, allowing a…
- risk 0.43cvss 7.7epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/agents/actions/:agent_id in api/server/routes/agents/actions.js loads an existing action with owner credentials and merges editor-controlled metadata.domain and…
- risk 0.43cvss 7.7epss 0.00
LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisor…
- risk 0.42cvss 7.6epss 0.00
LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the…
- risk 0.42cvss 6.5epss 0.00
LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups (/api/prompts/groups/:groupId). However, the request bodies are not…
- risk 0.42cvss 6.5epss 0.01
An unhandled exception in the danny-avila/librechat repository, version git 600d217, can cause the server to crash, leading to a full denial of service. This issue occurs when certain API endpoints receive malformed input, resulting in an uncaught exception. Although a valid JWT…
- risk 0.42cvss 6.5epss 0.00
An improper access control vulnerability (IDOR) exists in the delete attachments functionality of danny-avila/librechat version v0.7.5-rc2. The endpoint does not verify whether the provided attachment ID belongs to the current user, allowing any authenticated user to delete…
- risk 0.41cvss 6.3epss 0.00
In LibreChat 0.8.1-rc2, a logged-in user obtains a JWT for both the LibreChat API and the RAG API.
- risk 0.40cvss 6.1epss 0.00
LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, there is no handler for JSON parsing errors; SyntaxError from express.json() includes user input in the error message, which gets reflected in responses. User input (including HTML/JavaScript)…
- risk 0.39cvss 7.1epss 0.00
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…
- risk 0.37cvss 6.8epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/auth/2fa/verify-temp in api/server/routes/auth.js calls verify2FAWithTempToken and accepts repeated TOTP or backup-code guesses without a dedicated attempt limiter. An attacker…
- risk 0.37cvss 6.8epss 0.00
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server…
- risk 0.37cvss 5.7epss 0.00
A vulnerability in danny-avila/librechat allows attackers to exploit the unrestricted Fork Function in `/api/convos/fork` to fork numerous contents rapidly. If the forked content includes a Mermaid graph with a large number of nodes, it can lead to a JavaScript heap out of…
- risk 0.35cvss 6.5epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.9, GET /api/permissions/search-principals passes the q parameter to JavaScript RegExp construction and MongoDB regex queries in packages/data-schemas/src/methods/userGroup.ts…
- risk 0.35cvss 6.5epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, POST /api/messages/:conversationId authorizes req.params.conversationId in api/server/middleware/validateMessageReq.js but persists attacker-controlled req.body.conversationId through…
- risk 0.35cvss 6.5epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/auth/requestPasswordReset calls deleteTokens by user ID before creating a reset token, while password-reset and email-verification records in…
- risk 0.35cvss 6.5epss 0.00
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…
- risk 0.35cvss 6.5epss 0.00
LibreChat is a ChatGPT clone with additional features. Prior to 0.8.3-rc1, a Denial of Service (DoS) vulnerability exists in the DELETE /api/convos endpoint that allows an authenticated attacker to crash the Node.js server process by sending malformed requests. The DELETE…
- risk 0.35cvss 5.4epss 0.00
LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when a user posts a question, the iconURL parameter of the POST request can be modified by an attacker. The malicious code is then stored in the chat which can then be shared to other users. When…
- risk 0.35cvss 5.4epss 0.00
A vulnerability in danny-avila/librechat version 0.7.9 allows for HTML injection via the Accept-Language header. When a logged-in user sends an HTTP GET request with a crafted Accept-Language header, arbitrary HTML can be injected into the tag of the response.…
- risk 0.34cvss 6.3epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, packages/data-schemas/src/methods/file.ts updateFileUsage accepts chat attachment files[].file_id values without restricting the lookup to the authenticated owner. An authenticated…
- risk 0.34cvss 6.3epss —
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…
- risk 0.34cvss 6.3epss 0.00
LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the execute_code sandbox when persisting code-generated artifacts. On deployments using the default local file strategy, a malicious artifact filename containing…
- risk 0.34cvss 5.3epss 0.00
danny-avila/librechat is affected by an authorization bypass vulnerability due to improper access control checks. The `checkAccess` function in `api/server/middleware/roles/access.js` uses `permissions.some()` to validate permissions, which incorrectly grants access if only one…
- risk 0.34cvss 5.3epss 0.01
A vulnerability in danny-avila/librechat prior to version 0.7.6 allows for logs debug injection. The parameters sessionId, fileId, userId, and file_id in the /code/download/:sessionId/:fileId and /download/:userId/:file_id APIs are not validated or filtered, leading to potential…
- risk 0.34cvss 5.3epss 0.01
An improper access control vulnerability in danny-avila/librechat versions prior to 0.7.6 allows authenticated users to delete other users' prompts via the groupid parameter. This issue occurs because the endpoint does not verify whether the provided prompt ID belongs to the…
- risk 0.33cvss 6.1epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, client/src/components/Chat/Input/MCPConfigDialog.tsx renders the remote MCP details.description value through dangerouslySetInnerHTML without sanitization, allowing a malicious MCP server…
- risk 0.32cvss —epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. From 0.8.5 until 0.8.6, GET /api/user in api/server/controllers/UserController.js getUserController serializes federatedTokens and tokenset to the authenticated browser because an earlier…
- risk 0.30cvss 4.6epss 0.00
In danny-avila/librechat version v0.7.5-rc2, a vulnerability exists in the preset creation functionality where a user can manipulate the user ID field through mass assignment. This allows an attacker to inject a different user ID into the preset object, causing the preset to…
- risk 0.28cvss 4.3epss 0.00
LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control when querying agent permissions. An authenticated attacker can read the permissions of arbitrary agents, even if they have no permissions for this agent. LibreChat…
- risk 0.27cvss 5.3epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, unauthenticated POST /api/user/verify requests in api/server/routes/user.js call api/server/services/AuthService.js verifyEmail and return distinct responses for unknown, verified, and…
- risk 0.27cvss 5.3epss 0.00
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc2 through 0.8.2-rc3, the SSE streaming endpoint `/api/agents/chat/stream/:streamId` does not verify that the requesting user owns the stream. Any authenticated user who obtains or guesses a valid stream…
- risk 0.13cvss 3.1epss —
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.6, the POST /api/auth/login local-login validation path in api/strategies/localStrategy.js logs req.body, including the submitted plaintext password, during a Zod validation failure. The…
- risk 0.00cvss 5.9epss 0.00
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the POST /api/auth/2fa/backup/regenerate endpoint regenerates all 2FA backup codes without requiring any TOTP token or existing backup code verification. An attacker with a stolen…
- risk 0.00cvss 6.5epss 0.01
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the fix for CVE-2025-7105 added forkIpLimiter and forkUserLimiter rate limiters to POST /api/convos/fork to prevent rapid-fire conversation duplication. However, the POST…
- risk 0.00cvss 7.7epss 0.00
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, LibreChat allows users to configure custom OpenAI-compatible API endpoints by setting a baseURL. This URL is used to construct HTTP requests without any SSRF validation — no private…
Page 1 of 2