CVE-2025-9262

A flaw has been found in wong2 mcp-cli 1.13.0. Affected is the function redirectToAuthorization of the file /src/oauth/provider.js of the component oAuth Handler. This manipulation causes os command injection. The attack may be initiated remotely. The attack is considered to have high complexity...

mcp-cli 安全漏洞

mcp-cli is a model context protocol checker for Wong2 Personal Developer. A security vulnerability exists in mcp-cli version 1.13.0, which stems from an incorrect operation of the function redirectToAuthorization in the file /src/oauth/provider.js resulting in os command injection...

CVE-2025-54074

Cherry Studio is a desktop client that supports for multiple LLM providers. From versions 1.2.5 to 1.5.1, Cherry Studio is vulnerable to OS Command Injection during a connection with a malicious MCP server in HTTP Streamable mode. Attackers can setup a malicious MCP server with compatible OAuth...

Malicious code in mcp-menu (npm)

The package mcp-menu was found to contain malicious code...

Malicious code in mcp-opencage-server (npm)

The package mcp-opencage-server was found to contain malicious code...

MAL-2025-26053 Malicious code in mcp-menu (npm)

The package mcp-menu was found to contain malicious code...

Malicious code in auth0-mcp-server (npm)

The package auth0-mcp-server was found to contain malicious code...

MAL-2025-26054 Malicious code in mcp-opencage-server (npm)

The package mcp-opencage-server was found to contain malicious code...

SUSE CVE-2025-54424

1Panel is a web interface and MCP Server that manages websites, files, containers, databases, and LLMs on a Linux server. In versions 2.0.5 and below, the HTTPS protocol used for communication between the Core and Agent endpoints has incomplete certificate verification during certificate...

org.open-metadata:openmetadata-dist (>=1.0.0 <=1.13.0-snapshot), org.open-metadata:openmetadata-k8s-operator (>=1.12.0 <=1.13.0-snapshot) +1 more potentially affected by CVE-2025-50467 via org.open-metadata:openmetadata-service (>=1.0.0-alpha <=1.4.4)

org.open-metadata:openmetadata-service MAVEN version =1.0.0-alpha, =1.0.0, =1.12.0, =1.10.0, =1.13.0-snapshot Source cves: CVE-2025-50467 Source advisory: SNYK:JAVA-ORGOPENMETADATA-12009018...

org.open-metadata:openmetadata-dist (>=1.0.0 <=1.13.0-snapshot), org.open-metadata:openmetadata-k8s-operator (>=1.12.0 <=1.13.0-snapshot) +1 more potentially affected by CVE-2025-50468 via org.open-metadata:openmetadata-service (>=1.0.0-alpha <=1.4.4)

org.open-metadata:openmetadata-service MAVEN version =1.0.0-alpha, =1.0.0, =1.12.0, =1.10.0, =1.13.0-snapshot Source cves: CVE-2025-50468 Source advisory: SNYK:JAVA-ORGOPENMETADATA-11959222...

Command Injection

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Command Injection via libs/agno/agno/tools/mcp.py when handling the command argument. An attacker can execute arbitrary system commands by supplying crafted input...

Cursor <= 1.2.1 RCE (GHSA-4cxx-hrm3-49rm)

The version of Cursor installed on the remote host is 1.2.1 or prior. It is, therefore, affected by a remote code execution vulnerability. An attacker could achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or...

Cursor < 1.2.4 RCE (GHSA-24mc-g4xr-4395)

The version of Cursor installed on the remote host is prior to 1.2.4. It is, therefore, affected by a remote code execution vulnerability. Attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing...

GHSA-VF9J-H32G-2764 mcp-package-docs vulnerable to command injection in several tools

Summary A command injection vulnerability exists in the mcp-package-docs MCP Server. The vulnerability is caused by the unsanitized use of input parameters within a call to childprocess.exec, enabling an attacker to inject arbitrary system commands. Successful exploitation can lead to remote code...

Arbitrary Command Injection

Overview mcp-package-docs is an An MCP server that provides LLMs with efficient access to package documentation across multiple programming languages Affected versions of this package are vulnerable to Arbitrary Command Injection via unsanitized input passed to the exec function. An attacker can...

mcp-package-docs vulnerable to command injection in several tools

Summary A command injection vulnerability exists in the mcp-package-docs MCP Server. The vulnerability is caused by the unsanitized use of input parameters within a call to childprocess.exec, enabling an attacker to inject arbitrary system commands. Successful exploitation can lead to remote code...

Cursor AI Code Editor Vulnerability Enables RCE via Malicious MCP File Swaps Post Approval

Cybersecurity researchers have disclosed a high-severity security flaw in the artificial intelligence AI-powered code editor Cursor that could result in remote code execution. The vulnerability, tracked as CVE-2025-54136 CVSS score: 7.2, has been codenamed MCPoison by Check Point Research, owing ...

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...

CVE-2025-54135 Cursor Agent is vulnerable to prompt injection via MCP Special Files

Cursor is a code editor built for programming with AI. Cursor allows writing in-workspace files with no user approval in versions below 1.3.9, If the file is a dotfile, editing it requires approval but creating a new one doesn't. Hence, if sensitive MCP files, such as the .cursor/mcp.json file...