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...

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...

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...

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-2025-54136

Cursor is a code editor built for programming with AI. In versions 1.2.4 and below, attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing the file locally on the target's machine. Once a...

The vulnerability of the mcp-remote proxy server lies in its failure to eliminate special elements used in the operating system command, allowing attackers to execute arbitrary commands.

The vulnerability of the mcp-remote proxy server is related to the lack of measures taken to neutralize special elements used in the operating system commands. Exploiting this vulnerability allows a remote attacker to execute arbitrary commands...

The vulnerability of the mcp dev tool for testing and debugging MCP servers, MCP Inspector, allows a attacker to perform a CSRF attack.

The vulnerability of the mcp dev tool for testing and debugging MCP servers, MCP Inspector, is related to the lack of authentication for the critical function. Exploiting this vulnerability allows a remote attacker to perform a CSRF attack...

CVE-2025-54136

Cursor is a code editor built for programming with AI. In versions 1.2.4 and below, attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing the file locally on the target's machine. Once a...

Cursor 操作系统命令注入漏洞

Cursor is an AI code editor from Cursor open source. An operating system command injection vulnerability exists in Cursor 1.2.4 and earlier versions, which stems from the fact that the MCP configuration file can be modified, potentially leading to remote persistent code execution...

CVE-2025-54136

Cursor is an AI code editor where CVE-2025-54136 affects versions

CVE-2025-54136 Cursor's Modification of MCP Server Definitions Bypasses Manual Re-approvals

Cursor is a code editor built for programming with AI. In versions 1.2.4 and below, attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing the file locally on the target's machine. Once a...

CVE-2025-54133 Cursor's MCP Install Deeplink Does Not Show Arguments in its User-Dialog

Cursor is a code editor built for programming with AI. In versions 1.17 through 1.2, there is a UI information disclosure vulnerability in Cursor's MCP Model Context Protocol deeplink handler, allowing attackers to execute 2-click arbitrary system commands through social engineering attacks. When...

CVE-2025-54133

CVE-2025-54133 affects Cursor (code editor with AI features). The vulnerability lies in the MCP (Model Context Protocol) deeplink handler, where clicking a malicious cursor://anysphere.cursor-deeplink/mcp/install link can lead to execution of a full system command without showing the arguments in...

Cursor AI Code Editor Fixed Flaw Allowing Attackers to Run Commands via Prompt Injection

Cybersecurity researchers have disclosed a now-patched, high-severity security flaw in Cursor, a popular artificial intelligence AI code editor, that could result in remote code execution RCE. The vulnerability, tracked as CVE-2025-54135 CVSS score: 8.6, has been addressed in version 1.3 released...