AI / LLM Security Fundamentals
LLM trust boundaries, tool authorisation, RAG access, data handling, agents, evaluation and AI supply-chain controls.
Curriculum
Learn at your own paceModel, data and access boundaries
0/5 completedA five-question quiz follows this module.
Module quizzes
Use knowledge in a decision
Practice paths for this course
4 missions to explore
Poisoned context: the assistant’s boundary
A document retrieved by a support assistant requests an unexpected tool action. Separate information, instructions and authority.
Revoked access: the index remembers
Source access was revoked, yet AI retrieval returns an old chunk. Trace authority across the source, index and cache.
Delegated agent: the authority chain
An agent calls another tool and loses the user’s scope during delegation. Investigate identity, tool outputs and recovery boundaries.
Data lineage: new purpose, old copy
Pseudonymous customer data is requested for new analysis; a linkage table and supplier copy still exist. Manage the purpose change.
Final exam
Meet the required proficiency standard to earn your course certificate.
Academy finals require 80%; official exam requirements are assessed separately.