The Principle Of Least Autonomy. Every Agent Needs A Steering Wheel, Not Just A Sandbox Sandboxing is necessary but insufficient....
Technical Deep Dives
- All Posts
- Technical Deep Dive
- TDD
The Future Is Not Better Detections. What Claude Mythos Preview Means For The SOC Anthropic’s most capable model is now...
The Death Of The Ticket — How AI Is Redefining Security Engineering For Small Teams For solo security engineers and...
Traversing The Context Graph. AI Security Is The Precondition, Not The Constraint Context graphs let agents explain why decisions were...
How We Red-Teamed Our Own AI Agent. Lessons From Operation Pale Fire Three campaigns, two failures, one prompt injection hidden...
Claude’s Browser Extension Is A Hidden Channel Between Your Devices By Aner Morag Two devices logged into the same Anthropic...
The Browser Is The New Endpoint. Are You Treating It That Way? Island’s Michael Leland on enterprise browsers, agentic AI...
Finding Zero-Days With Any Model. Vulnerability Discovery Is An Orchestration Problem, Not A Frontier-Model Problem. The marquee finding from Anthropic’s...
Plan, Wait, Harvest: Zero-Click Data Exfiltration In Agentic AI. The attacker logs off after uploading one document. Weeks later, an...
I Tested 40 Humans And 16 AI Models On Security Code Review. None Of The Models Beat Human Effectiveness By...
What Your Architecture Says About Your AI Security Posture By Allie Howe It’s incredibly easy to make an AI agent...
From ‘Prompt and Pray’ to Provable Control By Josh Devon As the industry enters 2026, the proliferation of agentic behavior...
If You Can’t Threat Model It, You Can’t Secure It The T.E.S.T. Standard for AI Security Reviews By Teri Green-Manson...
I Tested The Top AI Coding Tools For Security Flaws. Ari Marzuk Interview by Confidence Staveley When Ari Marzuk, an...
My Friend Vibe-Coded An App And Asked If It Was Secure. So I Built A Tool To Find Out. Anshuman...
Vibe Coding Feels Like Magic. Here’s The Math That Keeps It Safe. By Krity Kharbanda Intro Vibe coding is one...
Cloudflare Sees 234 Billion Threats A Day. Here’s What Their New Field CISO Is Learning About AI. Liz Morton Interviewed...
AI Won’t Fix Your SOC. But It Can Sharpen Your Analyst’s Focus. By Sunnykumar Kamani The Traditional SOC Problem Static...
Can AI Fix The SOC Skills Gap? I Built A System To Find Out. By Victor Odico From Snort Rules...
I Asked My Browser’s AI A Simple Question. It Read My WhatsApp Messages To Answer. Rock Lambros on the least...
