Blog
Governance-first case studies
Analysis of real-world agent risk incidents and how governance-first design prevents them.
Agent Security
The Malware Skill Wake-Up Call — and Why the Real Fix Isn't a Scanner
The OpenClaw malware incident exposed a broken assumption in agent security. Scanners and registries won't fix it. Explicit authority will.
Read article
Agent Security
How Governance-First AI Would Have Prevented a Real-World Agent Malware Incident
A case study on how pre-execution policy, explicit authority, and human oversight would have stopped a real agent malware delivery path.
Read article
Agent Security
From Command Allowlists to Governance: What Agent Security Is Missing
A thoughtful manual hardening guide shows what it takes to run agents safely today — and why governance must move ahead of execution.
Read article