Community-powered security with AI: an open source framework for security research

Since its founding in 2019, GitHub Security Lab has had one primary goal: community-powered security. We believe that the best way to improve software security is by sharing knowledge and tools, and by using open source software so that everybody is empowered to audit the code and report any...

aiptx-cyber-mcp

Cyber MCPs - Security Tools for AI !MCP Securityhttps://...

📄 LibreChat MCP Remote Command Execution

LibreChat's Model Context Protocol MCP implementation contained a remote command execution vulnerability that allowed any authenticated user to execute commands as root on the Docker container. A single API request could trigger the exploit by taking advantage of the exposure of the stdio transpo...

Regular Expression Denial of Service (ReDoS)

Overview @modelcontextprotocol/sdk is a Model Context Protocol implementation for TypeScript Affected versions of this package are vulnerable to Regular Expression Denial of Service ReDoS in the UriTemplate processing when handling RFC 6570 exploded array patterns. An attacker can cause excessive...

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 1.25.1 and earlier versions, which stems from a regular expression denial of service in the UriTemplate class when...

CVE-2025-66580

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. A critical Stored Cross-Site Scripting XSS vulnerability exists in versions prior to 0.11.1 in the Mermaid diagram rendering component. The application allows the execution of arbitrary...

CVE-2025-66580 Dive has Cross-Site Scripting vulnerability that can escalate to Remote Code Execution

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. A critical Stored Cross-Site Scripting XSS vulnerability exists in versions prior to 0.11.1 in the Mermaid diagram rendering component. The application allows the execution of arbitrary...

EUVD-2025-204564

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. A critical Stored Cross-Site Scripting XSS vulnerability exists in versions prior to 0.11.1 in the Mermaid diagram rendering component. The application allows the execution of arbitrary...

CVE-2025-66580 Dive has Cross-Site Scripting vulnerability that can escalate to Remote Code Execution

Dive is an open-source MCP Host Desktop Application that enables integration with function-calling LLMs. A critical Stored Cross-Site Scripting XSS vulnerability exists in versions prior to 0.11.1 in the Mermaid diagram rendering component. The application allows the execution of arbitrary...

CVE-2025-68433

Zed, a code editor, has an aribtrary code execution vulnerability in versions prior to 0.218.2-pre. The Zed IDE loads Model Context Protocol MCP configurations from the settings.json file located within a project’s .zed subdirectory. A malicious MCP configuration can contain arbitrary shell...

CVE-2025-68433 Zed IDE MCP Context Server Configuration Arbitrary Code Execution

Zed, a code editor, has an aribtrary code execution vulnerability in versions prior to 0.218.2-pre. The Zed IDE loads Model Context Protocol MCP configurations from the settings.json file located within a project’s .zed subdirectory. A malicious MCP configuration can contain arbitrary shell...

CVE-2025-68433 Zed IDE MCP Context Server Configuration Arbitrary Code Execution

Zed, a code editor, has an aribtrary code execution vulnerability in versions prior to 0.218.2-pre. The Zed IDE loads Model Context Protocol MCP configurations from the settings.json file located within a project’s .zed subdirectory. A malicious MCP configuration can contain arbitrary shell...

CVE-2025-68433

CVE-2025-68433 affects Zed IDE prior to 0.218.2-pre. The vulnerability arises from loading MCP configurations from a project/.zed/settings.json without explicit user confirmation, allowing a malicious MCP to execute arbitrary shell commands on the host with the IDE user’s privileges when a projec...

Model Context Protocol Servers 参数注入漏洞

Model Context Protocol Servers is a large model context protocol server from Model Context Protocol open source. A parameter injection vulnerability exists in versions of Model Context Protocol Servers prior to 2025.12.17, which stems from the gitdiff and gitcheckout functions passing...

Model Context Protocol Servers 路径遍历漏洞

Model Context Protocol Servers is a large model context protocol server from Model Context Protocol open source. A path traversal vulnerability exists in versions of Model Context Protocol Servers prior to 2025.9.25, which stems from the gitinit utility accepting an arbitrary filesystem path and...

PT-2025-51936

Name of the Vulnerable Software and Affected Versions mcp-server-git versions prior to 2025.9.25 mcp-server-git versions prior to 2025.12.18 Description The Model Context Protocol Servers, specifically the mcp-server-git component, contains a flaw in the git init tool. Prior to version 2025.9.25,...

Quantigence: A Multi-Agent AI Framework for Quantum Security Research

Cryptographically Relevant Quantum Computers CRQCs pose a structural threat to the global digital economy. Algorithms like Shor's factoring and Grover's search threaten to dismantle the public-key infrastructure PKI securing sovereign communications and financial transactions. While the timeline...

mcp-exploit-demo-master

!Imagehttps://github.com/user-attachments/assets/2180e098-091...

CVE-2025-20381

In Splunk MCP Server app versions below 0.2.4, a user with access to the "runsplunkquery" Model Context Protocol MCP tool could bypass the SPL command allowlist controls in MCP by embedding SPL commands as sub-searches, leading to unauthorized actions beyond the intended MCP restrictions...

Securing the Model Context Protocol: Defending LLMs against Tool Poisoning and Adversarial Attacks

The Model Context Protocol MCP enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on...