Librechat

Librechat

45 Schwachstellen gefunden.

Hinweis: Diese Liste kann unvollständig sein. Daten werden ohne Gewähr im Ursprungsformat bereitgestellt.
6.5

CVE-2026-54027

Exploit
  • EPSS 0.2%
  • Veröffentlicht 25.06.2026 15:52:02
  • Zuletzt bearbeitet 26.06.2026 19:02:55

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the POST /api/files/images endpoint allows any authenticated user to upload files into any agent's tool_resources (e.g., context, execute_code) without ve...

8.1

CVE-2026-54036

Exploit
  • EPSS 0.19%
  • Veröffentlicht 25.06.2026 15:39:33
  • Zuletzt bearbeitet 26.06.2026 19:02:50

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.4-rc1, the GET /api/auth/2fa/enable endpoint can be called by an authenticated user (or attacker with a stolen session) even when 2FA is already fully enabled on...

8.1

CVE-2026-44654

Exploit
  • EPSS 0.27%
  • Veröffentlicht 02.06.2026 23:16:38
  • Zuletzt bearbeitet 04.06.2026 19:20:42

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 deletio...

6.5

CVE-2026-44653

Exploit
  • EPSS 0.28%
  • Veröffentlicht 02.06.2026 23:16:38
  • Zuletzt bearbeitet 04.06.2026 19:17:38

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`...

9.6

CVE-2026-32625

Exploit
  • EPSS 2.94%
  • Veröffentlicht 02.06.2026 23:16:35
  • Zuletzt bearbeitet 04.06.2026 19:08:10

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 val...

7.1

CVE-2026-31942

  • EPSS 0.21%
  • Veröffentlicht 02.06.2026 22:22:13
  • Zuletzt bearbeitet 04.06.2026 19:00:26

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 ...

6.3

CVE-2026-34371

Exploit
  • EPSS 0.26%
  • Veröffentlicht 07.04.2026 21:08:13
  • Zuletzt bearbeitet 14.04.2026 19:24:03

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 ar...

5.7

CVE-2026-31951

Exploit
  • EPSS 0.24%
  • Veröffentlicht 27.03.2026 19:29:25
  • Zuletzt bearbeitet 30.03.2026 20:29:45

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 cre...

5.3

CVE-2026-31950

Exploit
  • EPSS 0.21%
  • Veröffentlicht 27.03.2026 19:25:25
  • Zuletzt bearbeitet 30.03.2026 20:32:16

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 obtain...

7.7

CVE-2026-31945

Exploit
  • EPSS 0.25%
  • Veröffentlicht 27.03.2026 19:23:53
  • Zuletzt bearbeitet 30.03.2026 20:35:03

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-av...