// independent security research

Security research.
Evidence you can inspect.

I investigate security boundaries, build tools to inspect agent sessions, and measure what reaches exposed AI services. This is the research portfolio behind unauth.dev.

Published results. Runnable tools. Documented limits.

how a claim earns its place here
01 / State the boundary and the hypothesis. 02 / Run the deciding test and its negative control. 03 / Publish the evidence and what it cannot establish.
Code, measurement, and the judgment to revise a claim.
01

Three ways into the work

02

Tools and data you can use

03

Built through investigation

I am a security engineer publishing independent work through unauthdev. The contribution is the complete investigation: choosing the test, building the instrument, checking the result, and narrowing the conclusion when the evidence demands it.

About the work / All projects and maintenance status