SecurityWeek

GitLab Patches Code Execution, Information Disclosure Vulnerabilities

GitLab CE/EE security updates resolve 13 vulnerabilities, including high-severity code execution and information disclosure ...

Microsoft fixes AutoGen Studio flaw that enabled code execution

A vulnerability chain dubbed AutoJack in Microsoft's AutoGen Studio interface for prototyping AI agents could let attackers ...
The Hacker News

AutoJack Attack Lets One Web Page Hijack AI Agent for Host Code Execution

Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
Microsoft

Crypto Clipper uses Tor and worm-like propagation for persistence and control

Microsoft Threat Intelligence analyzed a cryptocurrency clipper campaign that combines clipboard theft, wallet replacement, ...
Bleeping Computer

Microsoft patches Exchange Server zero-day exploited in attacks

Microsoft has patched an actively exploited Exchange Server vulnerability that allows threat actors to execute arbitrary JavaScript code in cross-site scripting (XSS) attacks targeting Outlook Web ...
GitHub

nano-claw

nano-claw/ ├── src/ │ ├── agent/ # 🧠 Core agent logic │ │ ├── loop.ts # Agent loop (LLM ↔ tool execution) │ │ ├── context.ts # Prompt builder │ │ ├── memory.ts # Persistent memory │ │ ├── skills.ts ...
GitHub

Model Context Protocol servers

This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community-built servers and additional resources. Important If you are ...
LinkedIn

A Claude-Native Multi-Agent Test Automation System Using Model Context Protocol and and Retrieval-Augmented Knowledge Persistence

The system is structured around three core components: a seven-server Model Context Protocol (MCP) layer that provides agents with typed, LLM-optimized tool interfaces; a Retrieval-Augmented ...