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 OpenAI Agents SDK deployments — the handoff guardrail gap
Handoffs run through a different pipeline than tool calls, and the SDK's own documentation says tool guardrails don't apply to them. What that means for reviewing a multi-agent handoff chain.
What an AI Governance Committee actually needs in an evidence pack
The six artefacts an AI Committee needs to make a defensible decision, and the gaps that appear most often in evidence packs.
Reviewing CrewAI deployments — Crews, Flows, and the security the framework doesn't provide
CrewAI runs an estimated 450 million agents a month with, by its own maintainers' admission, no built-in auth, audit logs, or access controls in the open-source framework. What a review has to supply instead.
Reviewing LangChain and LangGraph agents — the serialization and checkpoint attack surface
Three real 2026 CVEs — a 9.3 serialization RCE, a path traversal, and a checkpoint SQL injection — show where LangChain and LangGraph's trust boundaries actually sit. The review questions that would have caught each one.
ISO 42001 audit readiness — the controls that fail most often
ISO 42001 audits surface the same gaps: incomplete risk registers, missing triggers, intent-not-practice evidence. Close them first.
Security review for agentic AI procurement — a buyer's checklist
Eight security areas procurement teams must address before an agentic AI system reaches production. A structured buyer checklist.
LLM output validation — the controls that actually work
Prompt injection and hallucination are symptoms of missing output validation. The controls that close the gap at each gate.
What goes in an AI risk register — and what does not
What belongs in an AI risk register: five required fields, common items that do not belong, and how to avoid a generic IT risk list with 'AI' added.
Threat modeling a RAG pipeline — retrieval, context, and generation risks
RAG introduces three attack surfaces standard LLM threat models miss: retrieval boundary, context window, generation gate.
DPAs and AI systems — what DPOs actually need to document
Data Protection Authorities are asking about AI in DPA reviews. What DPOs must document and the gaps regulators find first.
Attack path analysis for AI systems — beyond CVE scoring
CVE scores show a vulnerability exists. Attack path analysis shows if it is reachable and connected to meaningful blast radius.
AI incident response — what the playbook needs that IT playbooks miss
AI incidents have non-deterministic reproduction, model-level root cause, and degrading evidence. What the playbook must add.
Free resources
Practical templates for every framework covered here.
AI Security Review Template
Full review pack with threat model, controls, and evidence grading.
OWASP Agentic Top 10 Controls
Each risk mapped to required controls and lifecycle gates.
AI Risk Disposition Memo
Clearance decision template with rationale and sign-off log.
AI Go-Live Security Checklist
Production gate checklist for security architects and CISOs.