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.
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.
Reviewing how an AI vendor handles your data
Is your data used for training? Who accesses it? Where is it stored? The DPA rarely answers these. The data-handling review for AI vendors.
NIST AI RMF vs ISO 42001 — Which Framework to Choose
NIST AI RMF vs ISO 42001: the two leading AI governance frameworks compared across structure, certification, and evidence.
Securing an internal MCP server exposed to agents
Internal MCP servers exposing tools, databases, or APIs to agents have different security requirements than public ones. The review checklist.
General-purpose AI obligations under the EU AI Act
GPAI provisions create obligations for foundation model providers. What they mean and what deployers of GPAI-powered systems need to know.
Evaluating a RAG pipeline for security, not just relevance
RAG evaluation frameworks measure relevance. Security evaluation asks: what boundaries are crossed, what can be extracted, and what enforces the scope?
Agentic AI Privilege Escalation — 5 Attack Paths
Agentic privilege escalation needs no kernel exploit — just a model convinced to invoke unintended tools. Maps escalation paths and blocking controls.
LLM Excessive Agency — Scope Permissions Down (OWASP)
Excessive agency: an LLM has more capability than its task requires, and a manipulated model can exercise the excess. Least-privilege is the fix.
Re-assessment triggers — the field most dispositions skip
A disposition without re-assessment triggers never expires. Triggers keep decisions honest as AI systems evolve. How to define them.
Design-time vs runtime AI security — where review belongs
Runtime tools watch production anomalies. Design-time review decides if the system should ship. Conflating them creates gaps.
When to re-assess an AI vendor
AI vendor assessments expire. Model updates, new features, changed terms, incidents, and expanding use cases all trigger a fresh review.
The ISO 42001 evidence checklist for security reviews
Every evidence artifact an ISO 42001 audit will request, mapped by control domain and aligned to what AI security reviews already produce.
Prompt-context injection through MCP tools
MCP tools return data injected into model context. When that data contains instructions, the tool becomes an injection vector. Controls that prevent it.
Free resources
Practical templates for every framework covered here.
AI Security Review Template
Full evidence pack with threat model, controls, and evidence grading.
OWASP Agentic Top 10 Controls
Each risk mapped to required controls and lifecycle gates.
Decision Memo
Clearance decision template with rationale and sign-off log.
AI Go-Live Security Checklist
Production gate checklist for security architects and CISOs.