AI Security
Indirect prompt injection: why your AI agent reads attacker instructions
How instructions hidden in emails, web pages and documents reach an agent, and the controls that stop them acting on it.
Resources
Research and field notes
Practical writing on AI threats, AI governance and running a security programme with a small team. New articles every two weeks.
AI Governance
ISO/IEC 42001 for a 50-person company: what it takes
A practical scope, the documents you actually need, and how long readiness takes for a small team.
Virtual CISO
The first 90 days with a virtual CISO
What a good vCISO delivers in week 1, month 1 and month 3, and how to measure it.
Data Security
PDPA and generative AI: using customer data in AI tools
When consent is needed, what to put in your notices, and how to set up AI tools safely.
AI Security
Securing MCP servers: a checklist for engineering teams
Authentication, tool scoping, logging and supply-chain checks for Model Context Protocol servers.
Virtual CISO
A one-page cyber risk report your board will read
A template and the five numbers directors should see every quarter.
Get started
Want these in your inbox?
Get a short email when we publish new research. No marketing, and you can unsubscribe any time.