August 9, 20265 min read
The Autonomous Part Was The Part That Failed
Unit 42 recovered a full offensive AI session because the agent served its own operator to the internet, and the transcript shows where the automation stopped working
Research / Tag
agentic-ai
9 articles tagged agentic-ai
August 11, 20265 min read
When Your AI Red Team Becomes Your SOC
Detection infers that something happened. Exploitation proves what is possible. We are pouring agents into the half that can only ever guess, and leaving the half that produces receipts to a quarterly pentest.
August 21, 20266 min read
The Agent Never Broke the Sandbox. It Didn't Have To.
Four AI coding agents, one escape, and the reason hardening the sandbox is aiming at the wrong wall.
August 26, 20266 min read
Everything Is a Plugin Is a Security Statement
DeepSeek's harness writes down what every agent runtime has quietly asked you to trust, and being able to read it is the most useful thing about it.
August 31, 20265 min read
Your Agent's Memory Is a Supply Chain
Persistent identity files turn one compromised agent into a writer inside the next agent's trusted context.
August 8, 202611 min read
The Attacker Stopped Being a Person
Point the try-score-rewrite loop at your own product before a stranger points one at it, and put your judge under harder scrutiny than your generator
August 10, 202614 min read
What the Red Team Demos Don't Show You
A real overnight run produced 41 findings. Eleven were real, thirty were invented, and three targets were touched that should never have been touched. Here is how to run an autonomous agent so that arithmetic works for you.
August 17, 202614 min read
You Do Not Fix an Agent by Making It Smarter
Every autonomous agent fails in the same seven ways, and the order is predictable because the same conditions trigger each one. Every fix is the same move: take the creative core you cannot trust and wrap it in something deterministic that you can.
August 31, 20269 min read
Don't Try to Make an Agent Deterministic
A serious agent needs a playbook, a harness, hard boundaries, and an operator who owns the decisions the system cannot score.