CVE-2025-35028

By providing a command-line argument starting with a semi-colon ; to an API endpoint created by the EnhancedCommandExecutor class of the HexStrike AI MCP server, the resultant composed command is executed directly in the context of the MCP server’s normal privilege; typically, this is root. There...

Command Injection

Overview stata-mcp is a Let LLM help you achieve your regression analysis with Stata Affected versions of this package are vulnerable to Command Injection via the statado tool’s handling of Stata do-files. The server executes user-provided or LLM-generated do-files with subprocess.Popen...,...

Race Condition within a Thread

Overview mcp-mesh is a Kubernetes-native platform for distributed MCP applications Affected versions of this package are vulnerable to Race Condition within a Thread due to a Race Condition in Access Control. The agent shutdown process fails to atomically remove agents from the registry before...

Command Injection

Overview mcp-docker is a Model Context Protocol server for Docker management with AI assistants Affected versions of this package are vulnerable to Command Injection due to insufficient validation of list-format commands in the dockerexeccommand tool. The dockerexeccommand tool accepts a...

Incorrect Authorization

Overview agent-mcp-gateway is an An MCP gateway that aggregates your existing MCP servers and lets you define which servers and individual tools each agent or subagent can access. Solves Claude Code's MCP context window waste where all tool definitions load upfront instead of being discovered whe...

CVE-2025-66454

creationtimestamp| type| source ---|---|--- 2025-12-02 00:58:19+00:00| published-proof-of-concept| https://github.com/ArcadeAI/arcade-mcp/security/advisories/GHSA-g2jx-37x6-6438...

EUVD-2025-200116

MCP Watch has a Critical Command Injection in cloneRepo allows Remote Code Execution RCE via malicious URL...

MCP TypeScript SDK 安全漏洞

MCP TypeScript SDK is a Model Context Protocol open source developer toolkit for Model Context Protocol servers and clients. A security vulnerability exists in MCP TypeScript SDK versions prior to 1.24.0 that stems from not enabling DNS rebinding protection by default, which could lead to bypassi...

This Week in Spring - December 2nd, 2025

Hi, Spring fans! Welcome to another installment of This Week in Spring. By mistake, I inadvertently published older content in this installment, then tried to fix it and ended up re-publishing the same content. And, what's worse, I somehow ended up deleting the draft I had written for this...

CVE-2025-66401 MCP Watch has a Critical Command Injection in cloneRepo allows Remote Code Execution (RCE) via malicious URL

MCP Watch is a comprehensive security scanner for Model Context Protocol MCP servers. In 0.1.2 and earlier, the MCPScanner class contains a critical Command Injection vulnerability in the cloneRepo method. The application passes the user-supplied githubUrl argument directly to a system shell via...

CVE-2025-66401

MCP Watch vulnerability (CVE-2025-66401) affects MCPWatch

CVE-2025-66401 MCP Watch has a Critical Command Injection in cloneRepo allows Remote Code Execution (RCE) via malicious URL

MCP Watch is a comprehensive security scanner for Model Context Protocol MCP servers. In 0.1.2 and earlier, the MCPScanner class contains a critical Command Injection vulnerability in the cloneRepo method. The application passes the user-supplied githubUrl argument directly to a system shell via...

Malicious code in solana-dev-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c145bf7c5a5338ce094da7306d81c107eb218975e136423df4b1e3f71207b755 The package solana-dev-mcp was found to contain malicious code...

MAL-2025-191527 Malicious code in solana-dev-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c145bf7c5a5338ce094da7306d81c107eb218975e136423df4b1e3f71207b755 The package solana-dev-mcp was found to contain malicious code...

MCP Watch 操作系统命令注入漏洞

MCP Watch is a comprehensive security scanning program for Model Context Protocol servers by the individual developer Kapil Duraphe. An operating system command injection vulnerability exists in MCP Watch version 0.1.2 and earlier, which stems from command injection and could lead to arbitrary...

Deco Apps Library / MCP Servers 代码问题漏洞

Deco Apps Library / MCP Servers is a content management system from deco.cx open source. A code issue vulnerability exists in Deco Apps Library / MCP Servers version 0.120.1 and earlier, which stems from incorrect manipulation of the parameter url in the file website/loaders/analyticsScript.ts,...

CVE-2025-35028 HexStrike AI MCP Server Command Injection

By providing a command-line argument starting with a semi-colon ; to an API endpoint created by the EnhancedCommandExecutor class of the HexStrike AI MCP server, the resultant composed command is executed directly in the context of the MCP server’s normal privilege; typically, this is root. There...

CVE-2025-35028 HexStrike AI MCP Server Command Injection

By providing a command-line argument starting with a semi-colon ; to an API endpoint created by the EnhancedCommandExecutor class of the HexStrike AI MCP server, the resultant composed command is executed directly in the context of the MCP server’s normal privilege; typically, this is root. There...

CVE-2025-35028

HexStrike AI MCP Server is affected by a command-injection vulnerability in the EnhancedCommandExecutor API endpoint. A command-line argument starting with a semicolon (;) can cause a composed command to run with the MCP server’s privileges (typically root) because default configurations do not s...

PT-2025-48532

🚨 CVE-2026-1442 Since the encryption algorithm used to protect firmware updates is itself encrypted using key material available to an attacker or anyone paying attention, the firmware updates may be altered by an unauthorized user, and then trusted by a Unitree product, such as the Unitree Go2 a...