#ai agents

Kimi K3 and K3 Swarm: An Open-Weight Model Review from the Red Team Chair

A balanced cybersecurity review of Moonshot's Kimi K3 and the multi-agent K3 Swarm. Not "is it smart" but the question a red team actually asks: does an open, self-hostable, agentic model make you more effective on an engagement, and what does it give you that Claude and GPT cannot? Data that stays in the room, no vendor holding your engagement hostage, cost at scale, and a swarm that fits the work, weighed honestly against where the closed frontier models still win.

Aamir LakhaniJul 28, 202613 min read

Adversarial AI Offensive Security

The State of AI Automation: Zapier vs Make vs n8n, Through a Red Team Lens

AI automation quietly became critical infrastructure that security never signed off on. A deep look at where automation actually is in 2026, the real differences between Zapier, Make, and n8n, when to reach for each, and why every one of them is a beautiful new attack surface: standing credentials, unauthenticated webhooks, shadow automation, and prompt injection into agents that hold tools.

Aamir LakhaniJul 28, 202615 min read