Course

AI Security for Everyone

You don't need to be a hacker to use AI safely — but you do need to know where it can bite. This course walks through the real risks of everyday AI: how hidden text can hijack an assistant, why pasting secrets is dangerous, how to spot deepfakes and AI-written scams, what guardrails can and can't do, and how to keep your data private. Every idea is a drawn, interactive scene, and every lesson ends with one habit you can actually use.

8 lessonsBeginner46 min

Start the course Get the app

Course lessons

AI's new attack surface

Assistants read, act, and remember — opening doors a search box never did. Here's the shape of the risk.

›

Prompt injection

The signature AI attack: hidden text inside content the assistant reads quietly takes over what it does.

›

Don't paste secrets

A chat box feels private, but what you paste can be logged, reviewed, or used to train. Treat it like a postcard.

›

Deepfakes & voice clones

AI can fake a familiar voice or face convincingly. The defence isn't spotting pixels — it's verifying on another channel.

›

AI-written scams

AI removed the typos that used to give phishing away. Now you check structure — sender, links, and urgency.

›

Guardrails & jailbreaks

Models refuse harmful requests through a safety filter — but a clever "jailbreak" can slip past. Know what it can and can't do.

›

Your data & privacy

Chats can be retained, remembered, and used to improve models — but you hold the switches. Learn which to flip.

›

Staying safe: your habits

You don't need every trick memorised — just a few habits that quietly cover most AI risks.

›

Take the full course

Learn it properly — tracked & personalized

Follow the whole course as a guided journey — sequential lessons, progress, streaks and a personalized path, all in the app.

Get the app