Agentic Browsers Deleted the Same-Origin Policy. The Industry Can't Agree That's a Bug.
PleaseFix, Intent Collision, and what happens when the sandbox escape is the product
Aug 31, 20266 min read2
Command Palette
Search for a command to run...
Latest articles
The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document
What changed, what moved, and how to turn ten risks into ten controls
Aug 24, 20267 min read4
You Can't Govern What You Can't See - Building an AI Bill of Materials
The EU AI Act is here. Auditors will ask what your AI system is made of. Most teams can't answer. Here's how to fix that in one command.
Aug 19, 20268 min read
Your AI Agent Has Too Much Power -Auditing Excessive Agency
Two benign tools can combine into an exfiltration path neither has alone. Here's how to find it before an attacker does.
Aug 10, 20268 min read12
How a Machine-Learning Model Runs Code on Your Machine (and How I Scan for It)
A byte-level tour of pickle deserialization attacks, the 2025 scanner bypasses, and building a scanner that survives them.
Aug 3, 20269 min read3
I Built a Security Stack for AI Agents — Here's the Architecture
Airlock scans the parts. Warden scans the assembly. Manifest inventories it all.
Jul 27, 20268 min read9
Your AI Assistant Downloads Code From Strangers. Here's Why That's a Problem
A plain-English tour of why AI systems are riskier than they look — and what it takes to make them safe.
Jul 20, 20268 min read16
I Gave an AI Control of an 80,000-Seat Stadium — Here's How I Kept It on a Leash
Building a deterministic 3-tier agentic AI architecture with Google Antigravity, prompt-injection defenses, RBAC and Pydantic validation.
Jul 14, 202612 min read8