>_ open case file

Breach Casebook

Real breaches, taken apart by someone who has defended Fortune-100 platforms.

Watch on YouTube

About the channel

Each episode is a Case #N: a real breach or AI-security incident, rebuilt from public records, ending with a privacy fix you can use the same day. No hype, no product pitches. New cases arrive when they're ready.

Real breach post-mortems

Incidents rebuilt from public filings, court records and published reports. No rumours, no guesswork; "alleged" until a court says otherwise.

AI-security explainers

Prompt injection, hijacked AI agents, data leaking through assistants. How the attacks work, shown plainly, with safe demos where they help.

A fix you can use

Every case closes with a practical privacy or security step for regular people, not just security teams.

How we work

  1. The incident: what happened, in order, from the public record.
  2. The failure: which defenses should have stopped it, and why they didn't.
  3. The fix: what you can change on your own accounts and devices.

Public records first. People and organizations are described as "alleged" until a court convicts. If something is wrong, the correction goes in the pinned comment and the video description. This site and the channel are for education, not legal advice.

The casebook

CASE 01

The Email That Hijacks Your AI Assistant

Prompt injection, explained: how a single message can turn a helpful assistant against the person using it, and the settings that stop it.

Coming soon
CASE 02

MGM

Upcoming
CASE 03

Snowflake

Upcoming
CASE 04

Change Healthcare

Upcoming
CASE 05

xz-utils

Upcoming
CASE 06

Uber 2022

Upcoming

From the Breach Files

A case file being opened: the incident pulled from the public record, the failure laid out, a fix attached. That is the tone of the show.

Watch

New cases arrive when they're ready. They land on YouTube first.

Watch on YouTube