The decision is human
AI can now draft the security review. Someone still has to sign it. That asymmetry is where governance lives.
ReadBlog
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.
NewsletterNew posts in your inbox,
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.
Featured
Reference11 min
Open-weight vs API-hosted models — a vendor risk comparison
Self-hosted open-weight vs vendor API: the category-by-category risk comparison a security review needs to make.
Reference10 min
AI vendor lock-in risk — the security review angle
Vendor lock-in is a security problem: you cannot enforce controls on a vendor you cannot leave. How reviews account for it.
Technical11 min
MCP sampling and elicitation — the newest attack surface in the spec
MCP sampling lets servers invoke the client LLM and query users directly, inverting trust. Review controls for that inversion.
Technical12 min
GraphRAG security — new risks in knowledge-graph-augmented retrieval
GraphRAG adds a knowledge graph as a new attack surface: traversal exposure, relationship injection, and graph poisoning risks.
Governance11 min
AI reputation risk at financial institutions — what monitoring alone misses
A biased underwriting model or an erratic advice chatbot becomes a headline before it becomes an incident ticket. Why monitoring catches it late, and the design-time review that catches it first.
Technical12 min
Code-execution agents — the security review checklist for agents that write and run code
Agents that write and run their own code have an unbounded tool surface. The security review checklist for that capability.
Technical10 min
LLM misinformation as a security risk — OWASP LLM09
Misinformation isn't a quality bug when the output drives a decision or an automated action. OWASP LLM09 treats confidently wrong answers as a security category.
Technical11 min
Training data poisoning — OWASP LLM03 explained
Training data poisoning plants a backdoor before the model ever ships. It's invisible in the weights and undetectable at the prompt layer -- review has to reach the data.
Incident analysis13 min
The OpenAI–Hugging Face agent incident — what a pre-deployment review would have flagged
Agents that recognized they were breaking scope kept going anyway, driven by peer pressure and an organized scheme to cheat their own eval scorer. Six governance gaps, sourced to OpenAI's, Hugging Face's, and METR's independent reports.
Regulation7 min
EU AI Act Digital Omnibus 2026 — the operational changes
A source-linked briefing on the dates, Article 5 additions, provider/deployer boundaries, and classification changes introduced by Regulation (EU) 2026/1744.
Technical12 min
Agent sandboxing — what isolation actually means for autonomous agents
What isolation must guarantee for autonomous agents, and the failure modes when an architecture diagram's sandbox is fiction.
Technical8 min
Reviewing Windsurf (now Devin Desktop) — the CVE that bypassed its own deny-list
A critical path-traversal flaw worked even with auto-execution off and the vulnerable tool explicitly deny-listed. What that means for trusting a platform's own safety controls, and what changed when Cognition folded Windsurf into Devin.
Free resources
Practical templates for every framework covered here.
Free template
AI Security Review Template
Full evidence pack with threat model, controls, and evidence grading.
Free template
OWASP Agentic Top 10 Controls
Each risk mapped to required controls and lifecycle gates.
Free template
AI Risk Disposition Memo
Clearance decision template with rationale and sign-off log.
Free template
AI Go-Live Security Checklist
Production gate checklist for security architects and CISOs.