Data exfiltration and the lethal trifecta
An injection becomes serious when it lets data leave your system. This lesson teaches you to spot the possible leak channels in an AI product, check whether yours combines the three ingredients of the lethal trifecta and choose which one to remove before an attacker finds the gap.
Lesson objective
By the end of this lesson, you will be able to spot the channels through which an injection can get data out (tools, requests, images, links, RAG index), to say whether your product combines the lethal trifecta and to choose the element to remove.
Topics covered
- data exfiltration
- lethal trifecta
- RAG security
- AI agents
In the glossary
Where it fits
Data that leaks, actions that go wrong
How does an attack get data out or trigger actions, and where do you cut it off?
Lessons in this module
- Data exfiltration and the lethal trifecta (this lesson)
- Improper output handling, excessive agency and unbounded consumption
What you will learn in this module
This lesson is part of the course Secure an AI product: prompt injection, guardrails and the AI Act
- Map the attack surface of an AI product and its risks with the OWASP Top 10 for LLM Applications 2025, in a prioritized risk register.
- Analyze a product's direct and indirect prompt injection paths, system prompt leakage and data exfiltration (lethal trifecta).
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Build an AI assistant for your product
3 hr
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Design a RAG architecture that fits your product
3 hr 30 min
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Evaluate an AI feature: test sets, metrics and LLM judges
3 hr