Research & notes from the lab

Blogs
coming soon

We're writing up what we're learning about prompt injection, jailbreaks, PII redaction and secure AI browsing. Check back shortly — first posts are on the way.

Prompt injection

Anatomy of a real injection campaign

How a support bot was targeted in the wild — and what stopped it. Draft in progress.

PII & privacy

What actually leaks into AI chats

The most common data people paste into public AI tools — and how to redact it. Draft in progress.

Browser security

End-user browser security for AI era

Extensions, sessions and paste hygiene for teams using AI daily. Draft in progress.

Want it in your inbox?

Tell us what you want us to write about — or get a demo of the shield in the meantime.