CVE-2026-105740

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105699

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105697

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

CVE-2026-105740

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105740 Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105699 Langflow: Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105699

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105697 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

CVE-2026-105697

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

scopeblind-gateway

⚠️ This repository has moved. Active development continues at ScopeBlind/scopeblind-gateway. This personal fork may be behind the canonical repository. Please use the org repo for issues, pull requests, and the latest code. protect-mcp Security gateway for MCP servers. Shadow-mode logs by default,...

http-mcp-bridge

HTTP MCP Bridge Este proyecto implementa un servidor HTTP que actúa como puente entre peticiones HTTP/1.1 y un servidor MCP remoto, utilizando la librería mcp de Python GitHub. El propósito principal de esta iniciativa es poder utilizar herramientas de seguridad HTTP para probar servidores MCP...

firecrawl-mcp-server

Firecrawl MCP Server A Model Context Protocol MCP server that brings Firecrawl to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context. Big thanks to @vrknetha, @knacklabs for the initial implementation! Features Search the web and get full page...

Agent-Security-Regression-Harness

Arnés de Regresión de Seguridad de Agentes OWASP El Arnés de Regresión de Seguridad de Agentes OWASP es un arnés de pruebas de código abierto y neutral respecto al proveedor para ejecutar escenarios de regresión de seguridad ejecutables contra aplicaciones agénticas y sistemas integrados con MCP...

OWASP-WSTG-Rag

OWASP WSTG RAG Un sistema de Generación Aumentada por Recuperación RAG que indexa la OWASP Web Security Testing Guide WSTG en una base de datos vectorial, proporcionando acceso instantáneo a metodologías de pruebas de seguridad a través de API REST y MCP Model Context Protocol para la integración...

CVE-2026-52618

CVE-2026-52618 — @webfer/mcp-ansible-drupal: OS command injection via executeDeployment extra vars spawncmd0, cmd.slice1, shell: true re-joins an argument array into a single /bin/sh -c string without escaping, so a shell metacharacter in an extraVars value supplied to the executeDeployment MCP...

scopeblind-gateway

protect-mcp Puerta de política Cedar de fallo cerrado más recibos firmados para llamadas a herramientas de agentes de IA. protect-mcp es una puerta que se sitúa delante de las llamadas a herramientas de un agente de IA. Evalúa cada llamada contra una política Cedar el mismo lenguaje que AWS usa...

POC-CVE-2026-93680

Descripción Código de exploit de prueba de concepto para CVE-2026-93680 Uso Paso 1: Conectar a MCP SSE terminal 1 Paso 2: Inicializar la sesión MCP y listar las herramientas MCP terminal 2 Paso 3: Eludir la autenticación y exfiltrar datos terminal 1, resultado de salida del paso 2...

pyghidra-mcp

PyGhidra-MCP - Ghidra Model Context Protocol Server Overview pyghidra-mcp is a command-line Model Context Protocol MCP server that brings the full analytical power of Ghidra, a robust software reverse engineering SRE suite, into the world of intelligent agents and LLM-based tooling. It bridges...

pyghidra-mcp

PyGhidra-MCP - Servidor del Protocolo de Contexto del Modelo de Ghidra Visión general pyghidra-mcp es un servidor de línea de comandos del Protocolo de Contexto del Modelo MCP que trae todo el poder analítico de Ghidra, un robusto conjunto de herramientas de ingeniería inversa de software SRE, al...

CyberStrikeAI

CyberStrikeAI 中文 | English CyberStrikeAI 是 AI 原生网络安全的智能执行中枢——让意图转化为受治理的行动，让证据沉淀为运营记忆，并让每次行动优化下一次行动。 CyberStrikeAI 将规划、执行、人工监督、证据与复盘连接在同一个可审计工作空间中。项目基于 Go 构建，融合 Eino 智能体、MCP 原生工具、RAG 知识、可视化工作流以及攻击链建模与分析能力，面向已获得明确授权的安全任务。 从这里开始： 快速上手 · 中文文档 · 安全加固 !IMPORTANT 仅可对自有系统或已获得明确授权的目标使用...