CVE Watch21 jul 2026

CVE-2026-44653

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only `VIEW` ac

CVSS

6.5

Medio

EPSS

0.3%

p20

KEV

—

Exploit Today

0-100

Publicado: 2 jun 2026 · Última mod.: 21 jul 2026 · CWE-201

EPSS · 30d

0.3%EPSS · 30 días0.3%

2026-08-072026-09-04

Descripción técnica

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 config includes plaintext values for `apiKey.key` and `oauth.client_secret`. This allows viewers of a shared MCP server to exfiltrate the underlying provider credentials. Version 0.8..4 contains a patch. Other remediations include: never returning decrypted admin-managed secrets to non-owners; redacting apiKey.key and oauth.client_secret from all API responses consider returning only boolean presence indicators for secrets, similar to the auth-values route pattern; and, if owners need to edit configs without re-entering secrets, preserving secrets server-side and returning placeholders instead of plaintext.

Referencias oficiales

CVEs relacionados

CVECVSSEPSSKEVRExplotTítuloVis.

CVE-2026-853075.3 MED

9.5%

——3Insertion of Sensitive Information Into Sent Data vulnerability in Kevin Pirnie KP Agent Ready allows Retrieve Embedded Sensitive Data. This issue affects KP Agent Ready: from n/a before 1.2.08.2d CVE-2026-77123—

14.2%

——4Nexus Repository 3 contains a sensitive information disclosure vulnerability in the capability read API. An account holding the nexus:capabilities:read privilege can retrieve the plaintext shared secret configured on a webhook capability, which is intended to be masked from all API responses. This issue affects Nexus Repository 3 versions 3.2.0 through 3.95.x, and is fixed in version 3.96.0.3d CVE-2026-811625.3 MED

25.6%

——8Insertion of Sensitive Information Into Sent Data vulnerability in Drupal DXPR Builder: The Best Editing (AI) Experience for Drupal allows Forceful Browsing. This issue affects DXPR Builder: The Best Editing (AI) Experience for Drupal versions: from 0.0.0 to 2.8.1.3d CVE-2026-812806.5 MED

28.5%

——9Subscriber Sensitive Data Exposure in Print Barcode Labels for your WooCommerce products/orders <= 4.0.0 versions.4d CVE-2026-665857.5 ALT

15.6%

——5Unauthenticated Sensitive Data Exposure in WP Cafe Pro < 3.0.15 versions.12d CVE-2026-598094.9 MED

15.4%

——5SiYuan before v3.8.0 interpolates secret placeholders into the destination URL parameter of the http_request MCP tool, allowing attackers to exfiltrate stored secrets. An MCP client can craft a request with an attacker-controlled URL containing secret placeholders to send plaintext secret values to any public host without confirmation.14d