We provide virtual course about 10 AI Security for Agentic Applications. An agent is an LLM with tools, memory, and the ability to act across multiple steps without a human in the loop. Every capability that makes it useful also extends the blast radius.
Course description:
Classical AppSec controls assume code executes under a known identity with a defined permission set. Agents do neither.
What you´ll learn:
Module 1 - Indirect prompt injection:
• Attackers embed instructions in documents, emails, and web pages the agent will read; how a retrieval step becomes a remote code execution primitive.
Module 2 - Excessive agency and permission scope:
• Why least-privilege is harder when the agent decides what to do next, and how to enforcetool boundaries that survive adversarial inputs.
Module 3 - Memory poisoning:
• Persistent memory as a persistent attack surface; how malicious content survives across sessions and corruptsfuture decisions
Module 4 - Multi-agent trust:
• Orchestrator-to-subagent calls carry no verified identity by default; how trust degrades across a pipeline and what signing and scoping looks like in practice.
Module 5 - Human-in-the-loop design:
• Which decisions must pause for approval, how to make checkpoints tamper-evident, and what irreversibility means as a security property.
Instructor: Mohammad Yassin
I bring more than 15 years of experience from the IT industry, combining deep technical expertise, strong business acumen, and a proven ability to teach, train, and inspire teams. I`m both a technical architect, AI trainer, and commercial business builder, with a background in software engineering, IT architecture, and AI, as well as leadership roles as Head of Software Engineering & Technology and Head of Business Development.
For many years, I have designed and delivered courses, workshops, and learning programs for both technical and non-technical audiences, translating complex technology into clear, practical, and actionable knowledge.
Alongside this, I have hands-on experience building, selling, recruiting, and scaling successful business units, which gives me a strong understanding of both the technology and the commercial realities around it. My strength is helping organisations turn AI from an abstract opportunity into real capability, confident adoption, and measurable business impact.
Target audience:
Senior Engineers, AppSec Leads, Architects
Prerequisites:
• AI Security for LLM Applications, or equivalent experience
Language:
• English course material, english or norwegian speaking instructor
Course material:
The course fee includes digital course documentation