sigma-ai

AgentShield Sigmaルール このリポジトリの目的 このリポジトリには、AIエージェントが攻撃されたり操作されたりしていることを特定するのに役立つ検知ルールが含まれています。これは「脅威シグネチャ」のライブラリのようなものです。各ルールは、エージェントのログデータと照合されたときに、何か不審なことが起きていることを示すパターンを記述します。 AgentShield...

ai-tool-poisoning-guard

ai-tool-poisoning-guard 适用于 Claude Code、Codex 和 Cursor 的最低安全基线规则。这条免费规则弥补了各工具内置审查中的真实缺口。完整规则集 + 实施指南：Gumroad 链接 — 即将推出 。 你的 AI 编程助手会审查代码。但它不会审查随工具一起出现的那句话。 Claude Code、Codex 和 Cursor 都内置了某种形式的安全审查。但默认情况下，它们都不会将 MCP 工具描述 ——纯自然语言文本——视为需要与代码同等审查力度的输入面。 缺口所在： 当你添加一个 MCP...

UAP-protocol

root@kitploit: ██╗ ██╗ █████╗ ██████╗ ██║ ██║██╔══██╗██╔══██╗ ██║ ██║███████║██████╔╝ ██║ ██║██╔══██║██╔═══╝ ╚██████╔╝██║ ██║██║ ╚═════╝ ╚═╝ ╚═╝╚═╝ Universal Agent Protocol Un protocolo de comunicación unificado y centrado en la seguridad para el acceso a herramientas, la coordinación de agentes ...

mcp-doorman

mcp-doorman MCP 服务器的安全网关——每次工具调用都要在门口接受检查。 CI npm License: Apache-2.0 PRs welcome mcp-doorman 是一个即插即用代理，位于你的 AI 智能体（Claude Desktop、Claude Code、Cursor、VS Code 或任何 MCP 客户端）与其使用的 MCP 服务器之间。一条命令，零基础设施，每个 tools/list 和 tools/call 都会经过一个防护管道： 🛂 策略引擎 —— 按工具设置的允许/拒绝/需要批准规则，支持 glob 匹配 🕵️ 秘密信息擦除 —— AWS...

leash-poc

leash-poc: MCP tool-poisoning, contained by an independent pol...

mcp-tool-poisoning-poc

mcp-tool-poisoning — Educational PoC Demonstrates the Too...

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol MCP has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client...

CVE-2026-25805 Zed does not show Parameter Values for MCP Tool Calls. Users cannot detect tool poisoning.

Zed is a multiplayer code editor. Prior to 0.219.4, Zed does not show with which parameters a tool is being invoked, when asking for allowance. Further it does not show after the tool was being invoked, which parameters were used. Thus, maybe unwanted or even malicious values could be used withou...

mcp-exploit-demo-master

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

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...

Automatic Red Teaming LLM-Based Agents with Model Context Protocol Tools

The remarkable capability of large language models LLMs has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol MCP tools have become the de facto standard and are now widely...

MCP Server Tool Poisoning

Model Context Protocol MCP Server Tool Poisoning occurs when malicious actors manipulate tool configurations or metadata on a malicious MCP server. This can lead to the execution of unauthorized commands, data corruption, or the deployment of malicious tools. Such vulnerabilities are particularly...

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

Although Foundation Models FMs, such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced tool calling-triggering a proliferation of frameworks with...

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem

The Model Context Protocol MCP is an emerging standard designed to enable seamless interaction between Large Language Model LLM applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server...

Researchers Demonstrate How MCP Prompt Injection Can Be Used for Both Attack and Defense

As the field of artificial intelligence AI continues to evolve at a rapid pace, fresh research has found how techniques that render the Model Context Protocol MCP susceptible to prompt injection attacks could be used to develop security tooling or identify malicious tools, according to a new repo...