prompt-injection
5 free lessons tagged prompt-injection across Business, AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
The Risk You Bring In: Your Own AI Tools
The other direction of the problem. Employees using AI tools create exposure through data leaving the organisation, prompt injection turning an assistant against its user, malicious extensions, and code suggestions nobody verified. This lesson covers what to worry about and what is overstated.
Building the Control Layer: Rails, Classifiers, and Containment
Guardrails are a layered control system around a model that cannot police itself. This lesson covers the rail types, rules versus classifiers versus model-based judges, the tools that implement them, the latency and false-positive budget that constrains every design, and why architectural containment beats filtering.
The LLM Threat Model: Why the Model Cannot Defend Itself
Guardrails exist because a language model cannot reliably distinguish instructions from data. This lesson builds the threat model: the OWASP Top 10 for LLM Applications, direct and indirect prompt injection, jailbreaks, data leakage, and why tool-using agents turn a content problem into a security one.
Agentic Commerce: Trust, Liability, and What Breaks
Scoped tokens and signed mandates solve authorization, not everything. This lesson covers the unsettled parts: who is liable when an agent buys wrong, why merchants and agents have opposing incentives, prompt injection as a new attack surface at checkout, agent-to-agent buying, and why the market forecasts disagree by an order of magnitude.
Prompt injection: the security flaw at the heart of LLM apps
Why LLM apps are uniquely vulnerable to attacks delivered as plain text, the difference between direct and indirect injection, and the defences that actually help (plus the ones that don't).