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.

Technical11 min

Data poisoning in RAG knowledge bases

A RAG knowledge base is only as trustworthy as the documents in it. Data poisoning attacks insert malicious content into the knowledge base — not to corrupt the index, but to influence model outputs when those documents are retrieved.

Regulation10 min

Building an EU AI Act system inventory

The EU AI Act requires organisations to know which AI systems they deploy and which tier each one falls into. Building that inventory is harder than it sounds when AI is embedded in SaaS, vendor products, and internal tooling.

Technical12 min

Mapping the agentic AI attack surface

The agentic AI attack surface has five distinct layers: the prompt channel, the tool surface, the memory layer, the orchestration boundary, and the output channel. This piece maps each layer with its associated threats and controls.

Technical12 min

Prompt injection, explained for security reviewers

Prompt injection is the most widely discussed LLM attack and the most widely misunderstood. This piece cuts through the confusion: what it is, what its variants are, how it differs from SQL injection, and what controls actually reduce the risk.

Reference12 min

The AI security review checklist, by lifecycle gate

A checklist that follows the lifecycle of an AI system — intake, architecture, threat model, control plan, disposition, pilot, production. Each gate has different review questions and different evidence requirements.

Reference12 min

The NIST AI RMF, explained for practitioners

The NIST AI Risk Management Framework gives organisations a structure for managing AI risk across four functions: Govern, Map, Measure, and Manage. This piece explains each function in terms a security practitioner can act on.

Reference10 min

The AI section your vendor security questionnaire is missing

Standard vendor security questionnaires cover data processing agreements, SOC 2, and encryption. They do not cover model governance, re-assessment triggers, or incident notification for model updates. This piece fills the gap.

Governance11 min

Writing an AI governance committee charter

An AI governance committee without a charter is a meeting with a name. The charter defines the committee's authority, composition, quorum, decision types, and escalation paths. This piece defines what a working charter requires.

Technical11 min

MCP security — the four attack surfaces of a Model Context Protocol server

MCP servers extend a model's capabilities by exposing tools, resources, and prompts. Each extension point is an attack surface. This piece defines the four surfaces and the review questions for each.

Reference12 min

ISO 42001, explained for security teams

ISO/IEC 42001 is the international standard for AI management systems. This piece explains what it requires, how it differs from ISO 27001, and what a security team needs to know to support an AIMS implementation or certification.

Technical10 min

RAG security — the three boundaries that matter

Retrieval-augmented generation adds a retrieval layer between the user and the model. That layer has three security boundaries — the data boundary, the retrieval boundary, and the context boundary — and each has distinct failure modes.

Regulation11 min

EU AI Act risk tiers, explained for engineers

The EU AI Act classifies AI systems into four risk tiers: unacceptable, high, limited, and minimal. The classification determines the obligations. This piece explains how to classify a system and what each tier requires.