Blog

The thinking behind AI security review.

Threat models, governance evidence, and the decisions that hold up under scrutiny. Written for security architects and the committees they report to.

Newsletter

New posts in your inbox,
when they publish.

Threat modeling, governance evidence, and what AI Committees actually need — written for security architects and AI governance leads. No cadence promises.

No spam. Unsubscribe anytime.

Regulation10 min

The EU AI Act timeline and what to prepare first

The EU AI Act applies in phases. Different provisions came into effect at different dates, and the obligations for high-risk systems differ from those for GPAI. This piece maps the timeline and the preparation steps that deliver the most value first.

Reference14 min

The OWASP Agentic Top 10, explained for security reviewers

The OWASP Agentic Top 10 identifies the ten highest-risk threat categories for agentic AI systems. This walkthrough explains each one in terms a security reviewer can act on, with the controls and evidence requirements for each.

Technical10 min

System prompt leakage and why it matters for security

System prompts encode assumptions, scoping rules, persona instructions, and sometimes credentials. When they leak, they expose the system's trust model. This piece explains why this matters more than most teams believe.

Technical11 min

The AI bill of materials (AI-BOM) for security review

An AI bill of materials documents the components of an AI system: base models, fine-tuning datasets, inference infrastructure, plugins, and dependencies. It is the foundation of a security review and a requirement under several emerging governance frameworks.

Foundations9 min

A lightweight AI security review for fast-moving teams

Large-enterprise review processes do not scale to a 10-person team shipping an AI feature next sprint. This piece defines the minimum-viable AI security review: three questions, three artefacts, one decision record.

Foundations10 min

What makes an AI decision record defensible

A defensible AI decision record is one that a regulator, auditor, or procurement officer can read — without access to the people who made the decision — and understand what was decided, why, and what commitments were made. This piece defines the standard.

Regulation10 min

Reviewing how an AI vendor handles your data

What happens to the data you send to an AI vendor? Is it used for training? Who can access it? Where is it stored? These questions are not always answered in the DPA. This piece defines the data-handling review for AI vendors.

Reference12 min

NIST AI RMF vs ISO 42001 — choosing a governance backbone

The NIST AI RMF and ISO 42001 are the two most widely adopted AI governance frameworks. This piece compares them across five dimensions — structure, audience, certification, integration, and evidence — to help organisations choose a starting point.

Technical10 min

Securing an internal MCP server exposed to agents

Internal MCP servers — built to expose internal tools, databases, or APIs to agents — have different security requirements than public MCP servers. This piece defines the review checklist for an internally-hosted MCP server.

Technical11 min

Evaluating a RAG pipeline for security, not just relevance

RAG evaluation frameworks are designed to measure retrieval quality and answer relevance. Security evaluation asks different questions: what data boundaries does the pipeline cross, what can be extracted, and what controls enforce the intended scope?

Regulation11 min

General-purpose AI obligations under the EU AI Act

The GPAI provisions of the EU AI Act introduce obligations for foundation model providers. This piece explains what GPAI means, which obligations apply, and what deployers of GPAI-powered systems need to understand.

Technical12 min

Privilege escalation paths in agentic AI

Agentic AI privilege escalation does not require a kernel exploit. It requires a model that can be convinced to invoke a tool it was not intended to invoke. This piece maps the escalation paths and the review controls that block them.