Blog
Blog
Original writing on AI security, agentic systems, and offensive research.
Blog index
24 posts
PostCategoryDate
Both Frontier Labs Broke Containment. The Exploits Were Boring.
NewsAI & Cyber IntelligenceOpenAI Paused Astra for Cyber Risk, Then Sold Cyber Access
NewsAI & Cyber IntelligenceThree AI Attacks This Week, Not One New Way In
NewsAI & Cyber IntelligenceThe Autonomous Part Was The Part That Failed
PulseAI Threat PulseWhen Your AI Red Team Becomes Your SOC
PulseAI Threat PulseThe Agent Never Broke the Sandbox. It Didn't Have To.
PulseAI Threat PulseEverything Is a Plugin Is a Security Statement
PulseAI Threat PulseYour Agent's Memory Is a Supply Chain
PulseAI Threat PulseThe Attacker Stopped Being a Person
SeriesAgentic AI Red TeamWhat the Red Team Demos Don't Show You
SeriesAgentic AI Red TeamYou Do Not Fix an Agent by Making It Smarter
SeriesAgentic AI Red TeamDon't Try to Make an Agent Deterministic
SeriesAgentic AI Red TeamEveryone Selling You an AI Agent Isn't Telling You the Whole Truth
SeriesAgentic AI OffSecAgentic AI Is a Weapon You Can't Aim
SeriesAgentic AI OffSecYour AI Agent Is Chaos. Tame It.
SeriesAgentic AI OffSecHow Do You Actually Hack an AI?
SeriesAgentic AI OffSecWhy MCP Is the Shadow IT of AI
NewsIndependent postYour First AI Red Team Skill: From Zero to Weaponized in 30 Minutes
SeriesField ManualReconnaissance at Machine Speed: AI-Powered Target Mapping
SeriesField ManualBuilding Adversarial Agents: Your First AI Hackbot
SeriesField ManualThe RAG Attack Playbook: Poisoning the Knowledge Base
SeriesField ManualAgent Kill Chains: When Jailbreaking Gets Dangerous
SeriesField ManualCoordinated Operations: Multi-Agent Red Team Campaigns
SeriesField ManualThe AI Pentest Report: From Raw Findings to Executive Deliverable
SeriesField Manual