CirriusTech
  • Home
  • Tech
  • Projects
  • Shop
  • Personal
  • Fiction
  • About
  • Certifications
☕ Enjoying the content? Consider supporting me on Ko-fi

Projects & Research

Tools, Research & Open Source

Security research, open source tooling, and experimental projects. Built to explore, understand, and solve real problems.

🔬

ISeeMP

Maps execution paths in MCP and agent tooling environments to show what an AI system can actually be made to do.

GitHub
🔬

m365-graph-schema-monitor

An offline-first tool for Microsoft Graph metadata snapshots, schema diffing, and change reporting.

GitHub
🔬

coding-agent-baselines

A curated set of instruction packs for consistent, secure, and maintainable AI-assisted software delivery.

GitHub
🔬

WhereMyMVPsAt

Public issue-intake repository for bug reports, feature requests, and responsible security reporting.

GitHub
🔬

Power Elevate

A PowerShell toolkit for provisioning, auditing, and documenting Windows permissions with least-privilege principles.

GitHub
🔬

dusk.li

A Hugo-powered directory that rates websites on dark mode support and color contrast accessibility.

GitHub
  • ««
  • «
  • 1
  • 2
  • 3
  • 4
  • »
  • »»
Recent Posts
The Bigger the Judge, the Better the Judgment? Not Quite.
The Bigger the Judge, the …

A few days ago, I published High Confidence Is Not a Security Control, having spent some time looking at JEV, a specialised decision model, and the security implications of allowing probabilistic AI judgments to drive consequential actions. The concern was straightforward: a model receives evidence, …

October 8, 2026 Read
"High Confidence" Is Not a Security Control
"High Confidence" Is Not …

AI security tooling keeps getting faster. Faster triage, faster classification, faster threat intelligence analysis, faster decisions. And, increasingly, faster automated action. That’s exciting, but it’s also where things start getting dangerous. I’ve been looking at JEV recently, …

October 2, 2026 Read
'A Human Should Check It' is Not an Agentic Security Control
'A Human Should Check It' …

A little while ago I demonstrated something fairly simple. An attacker-controlled HTTP User-Agent value was ingested into Microsoft Sentinel as part of normal security telemetry. Security Copilot then consumed that telemetry while analysing the incident. The User-Agent contained an indirect prompt …

September 30, 2026 Read
Continuous Access Evaluation: Is it really tho?
Continuous Access …

This is a personal blog and all content herein is my own opinion and not that of my employer. Background Continuous Access Evaluation, or CAE, is one of those security controls with a wonderfully descriptive name. Access is not supposed to be evaluated only when you first authenticate. It is …

September 16, 2026 Read
Daddy Issues: When APIM Workspaces Inherit the Parent Identity
Daddy Issues: When APIM …

This is a personal blog and all content herein is my own opinion and not that of my employer. Introduction Sometimes security research starts with an exploit. Sometimes it starts with a much more boring question: “Where is the actual security boundary?” This one started with the latter. …

September 14, 2026 Read
What The Entra Fudge?! Tenant Restrictions v1 Doesn't Mean What You Think It Means
What The Entra Fudge?! …

If you implemented Tenant Restrictions v1 and only validated Restrict-Access-To-Tenants, you may only have implemented half the control you think you have.

August 19, 2026 Read
Footer logo
© 2026 All Rights Reserved