Help CTOs and security teams understand the attack surface they’re creating when they deploy AI, and how to close it before it becomes an incident.
Apr 14, 2026
•
6 min read
I built a 3-agent coding system this week. First control I added: repo isolation on the write-capable agent.
Apr 8, 2026
5 min read
But only 6% of the security budgets cover it
Mar 31, 2026
7 min read
The payload ran as a systemd service. The Trivy scan still returned green. Nobody noticed.
Mar 24, 2026
The .env file is not an identity system. The ecosystem just forgot. Plus a CVSS 9.8 with no patch.
Mar 16, 2026
99% guardrail bypass, 95% RAG poisoning, and the one fix that addresses both.
Mar 9, 2026
One line in a Dockerfile stopped three containers, exfiltrated a full inventory, and the AI reported: “The image is safe to use.”