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.

Technical13 min

LLM red-teaming for a security review

Red-teaming an LLM is not pentesting it. Covers goal hijacking, jailbreaking, indirect injection, and exfiltration chains — with documentation guidance.

Foundations10 min

Five mistakes that make an AI security review undefensible

Five structural mistakes that make an AI security review indefensible. Found in nearly every review regardless of threat coverage.

Governance10 min

The security terms an AI vendor contract needs

Standard contracts miss AI-specific terms: model-change notice, training restrictions, incident notification, re-assessment rights. The clause language.

Governance11 min

Preparing for an ISO 42001 internal audit

What an ISO 42001 internal audit must cover, what evidence auditors want, and the gaps that appear most in first-time preparations.

Reference10 min

MCP Server Security Review Checklist (2025)

Structured checklist for MCP server review: transport, authentication, tool manifest, context injection surface, dependencies, and evidence requirements.

Technical10 min

Context-window risks in RAG and how to bound them

The context window is where queries and retrieved documents meet the model. Anything inside influences outputs. How to bound what gets in.

Technical11 min

Goal hijacking and instruction drift in autonomous agents

Goal hijacking makes an agent pursue unintended objectives. Instruction drift is the slow version. Both evade detection because the agent appears to work.

Technical12 min

Guardrails that work vs guardrails that look like they work

Most LLM guardrails are bypassable classifiers. Distinguish patterns that provide genuine risk reduction from those that only provide the appearance of it.

Governance10 min

What evidence an AI security review should produce

Review evidence must survive regulator questions, procurement audits, and post-incident inquiries. What it needs to include.

Governance10 min

Finding the AI vendors no one formally approved

Shadow AI is in every organisation. Where unapproved AI tools hide, how to find them, and how to formalise without alienating adopting teams.

Governance10 min

Roles and responsibilities under ISO 42001

ISO 42001 requires documented AI management roles. Who the standard expects, how they map to org structures, and what each must demonstrate.

Technical10 min

MCP security vs traditional API security — what changes

MCP looks like a REST API but the client is a non-deterministic model. The attack surface includes tool descriptions and trust sits at the model.