FILE 001
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 soonAbout the channel
Breach Files rebuilds real security incidents from the public record and explains the new attacks aimed at AI tools, in plain English, for people who use technology rather than defend it for a living.
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 file closes with a practical privacy or security step for regular people, not just security teams.
How each file works
- The incident: what happened, in order, from the public record.
- The failure: which defenses should have stopped it, and why they didn't.
- The fix: what you can change on your own accounts and devices.
Latest & upcoming files
FILE 002
Case file in preparation
A real breach post-mortem, rebuilt step by step from the public record.
In researchFILE 003
Case file in preparation
An AI-security explainer on the attacks aimed at AI agents and assistants.
In researchSubscribe
New files land on YouTube first. Subscribe so you don't miss the first one.