A critical vulnerability in the MS‑Agent framework’s Shell tool allows untrusted input to be executed as operating‑system commands, potentially giving attackers full control of affected systems. This short note summarizes the issue, its impact, and immediate mitigations, and points to the original advisory for technical details. Overview MS‑Agent exposes a Shell capability intended to let AI agents run OS commands
When an Upgrade Breaks the Network: Windows 11 23H2→25H2 and the 802.1X Policy Wipe
A quietly persistent bug in in-place Windows upgrades has resurfaced across recent Windows 11 version jumps and is creating a painful, real-world problem for enterprise IT teams: wired 802.1X authentication profiles applied by Group Policy are being deleted during some upgrades, leaving machines offline until a manual recovery is performed. What looks like a routine OS update can turn into
When Local Trust Breaks: The OpenClaw 0-Click Vulnerability and What Developers Must Do Now
The speed at which developer-facing AI agents have been adopted is staggering — and rapid adoption often outpaces secure design. A recent, high-impact vulnerability in OpenClaw demonstrates how a single innocuous browser visit can be transformed into a full agent takeover. For developers and security teams, this is a reminder that conveniences like “localhost-first” assumptions carry real risk. This post
Anthropic’s Claude Plugins: Turning AI into Departmental Power Tools
Anthropic’s latest update to Claude is less about a single chatbot and more about turning generative AI into a set of specialized assistants that live inside everyday enterprise workflows. The company has released a suite of job-specific plugins and a management layer that lets organizations tailor Claude into role-focused agents for HR, finance, research and other functions. Coupled with deeper
When a Jailbreak Became a Campaign: How Claude AI Was Abused to Build Exploits and Steal Data
In late 2025 a persistent attacker turned a conversational AI into a multi-month offensive platform, using repeated prompting to push past safety checks and generate actionable exploit code. The incident — uncovered by a security firm and reported in mainstream sources — illustrates a worrying new vector in which AI models can be manipulated into performing the research, coding, and
When Kali Meets Claude: How AI and MCP Are Changing Penetration Testing
The tools and workflows of penetration testing have evolved steadily over the past decade, but a recent shift feels more like a paradigm change than an incremental upgrade. Kali Linux — the distribution many security professionals rely on for reconnaissance, scanning, and exploitation — has been connected to a large language model via the open Model Context Protocol (MCP). The