Loading posts ...

Offensive AI Security

AI-Enabled Offensive Cyber Operations: Capabilities and Risks AI is continuing to transform offensive cyber capabilities through advances in large language models (LLMs), autonomous agents, and high-throughput inference systems. These technologies are enabling new forms of…
Read More

Skills, Connectors, Plugins, Oh My: A Security Practitioner’s Map of the Claude Extension Ecosystem

TL;DR Three primitives, one trust radius. Skills, Connectors (MCP), and Plugins look like distinct architectural units but are effectively a bundle. A single plugin installation…
Read More

Introducing ClaudeSec: A Community Knowledge Hub for Claude Ecosystem Security

The Claude ecosystem has moved faster than the practical security guidance around it. Connectors, desktop extensions, managed agents, and new deployment surfaces are shipping weekly…
Read More

Agent Skills Supply Chain Risks

Supply Chain Risks of Agent Skills AI agents are rapidly evolving from simple automation tools into complex systems capable of performing a wide range of…
Read More

Inside Claude Managed Agents: Reverse-Engineering the Security Boundaries of Anthropic’s Hosted Agent Runtime

In our previous deep dive into Claude Cowork, we reverse-engineered Anthropic’s desktop agent – uncovering gVisor syscall filtering, MITM TLS inspection proxies, and a layered…
Read More

Software Supply Chain Attack: How the AI Agent Ecosystem Became a New Battleground

The software ecosystem has undergone a fundamental shift with the emergence of AI agents. Applications are no longer built from isolated codebases. They are now…
Read More

Securing Claude Managed Agents: What You Need to Know Before Going to Production

Claude Managed Agents is Anthropic’s hosted agent runtime – a platform where Claude runs autonomously in cloud containers with bash access, file I/O, web browsing,…
Read More