IT training across Europe - tecnovy makes you future-ready.

tecnovy AI Suite

Offensive AI Security for Developers

The target application starts as a plain chat app and ends as an agent with tools. Module by module it gains a component, and with it a new class of attack: prompt injection, unchecked model output, data leakage through retrieved documents, hijacked agent goals. You run every attack yourself in the lab, and every lab ends with a review of the countermeasure in code. Finally you run automated attack tests as a gate in a CI pipeline.
Attendance certificate4.8/5 on ProvenExpert

What this module delivers.

Switching sides to build better: in tecnovy's Offensive AI Security for Developers you exploit flaws in LLM applications yourself and justify every fix in code. Your team then checks LLM features with automated attack tests in CI.

How the training runs

Method
About 60% hands-on labs, each ending in a fix review
Basis
tecnovy curriculum mapped to the OWASP GenAI Top 10 lists
Outcome
tecnovy certificate of participation at 80% attendance, no exam

Dates & booking

Choose a date that fits

4 dates

  • EUREuro
  • USDUS Dollar
  • CHFSwiss Franc

Sessions with this symbol offer up to 25% group discount. Click “Details & Registration” to learn more.

20 Apr 2027CEST
Tue
Online training Group Discount
Time zone CEST
Language German
Trainer
Seats 5+ seats
10% Earlybird Discount

990 €−99 €891 €

excl. VAT
22 Jun 2027CEST
Tue
Online training Group Discount
Time zone CEST
Language German
Trainer
Seats 5+ seats
10% Earlybird Discount

990 €−99 €891 €

excl. VAT
14 Sep 2027CEST
Tue
Online training Group Discount
Time zone CEST
Language German
Trainer
Seats 5+ seats
10% Earlybird Discount

990 €−99 €891 €

excl. VAT
23 Nov 2027CET
Tue
Online training Group Discount
Time zone CET
Language German
Trainer
Seats 5+ seats
10% Earlybird Discount

990 €−99 €891 €

excl. VAT

Fit

Who this module is designed for

Typical roles

  • You build chatbots, RAG systems or copilots on top of an LLM, or integrate them into existing applications.
  • You develop agents that call tools, and you decide what they are allowed to execute.
  • You are expected to test LLM features against attacks before release and to automate that testing.

Prerequisites

No prerequisites

You can start right away. What you need: basic Python or JavaScript, working knowledge of HTTP/REST and browser DevTools, your own laptop with Docker and Burp Suite Community Edition.

Consider instead AI Security & LLM Security For those who want to test models, applications and agents more broadly and plan safeguards up to monitoring and incident response.

Curriculum

Offensive AI Security for Developers Course in Detail

Six modules and a closing round. Each module extends the target application and follows the same sequence: short input, live demo of the attack, lab, review of the countermeasure. You map every finding to a category of the current OWASP lists.

01Attack surface and threat modelling

You map where an LLM application accepts input an attacker can control.

  • Trust boundaries: user input, system prompt, RAG context, tool calls, model output, agent memory
  • STRIDE-style threat analysis on a sample architecture
  • Retrieved documents and tool descriptions are potential attacker input too
  • Why static code analysis (SAST) and dependency scanning (SCA) do not see prompts and context
02Prompt injection and hidden context exposure

Here you get a chatbot to ignore its rules and give away its system prompt.

  • LLM01:2026 Prompt Injection: overriding roles, breaking delimiters, layering instructions
  • LLM08:2026 Hidden Context Exposure: extracting the system prompt
  • Why keyword filters fail: encoding, switching language, split payloads
  • Fix review: no secrets in the system prompt
03Output handling and excessive agency

Once the application passes model output on unchecked, it opens classic web flaws.

  • LLM10:2026 Improper Output Handling: XSS through responses rendered as HTML, SQL and command injection in the backend
  • LLM03:2026 Excessive Agency: functions such as deleting or sending email that the model does not need
  • Fix principles: treat output as data, context-aware encoding, tool allowlist, human approval for sensitive actions
04RAG, indirect injection and data exfiltration

Here you plant instructions in documents the application later loads as context.

  • Indirect prompt injection through documents, emails or tickets, the route behind EchoLeak (CVE-2025-32711) in Microsoft 365 Copilot
  • Data exfiltration through Markdown images and links that send data to an outside URL when rendered
  • LLM02:2026 Sensitive Information Disclosure and LLM09:2026 Vector and Embedding Weaknesses
  • Fix principles: separate retrieved content from instructions, restrict outbound links
05Agents and MCP

Once the model plans, remembers and calls tools through the Model Context Protocol (MCP), you attack its goals and permissions.

  • ASI01 Agent Goal Hijack: redirecting the goal through content the agent reads
  • ASI02 Tool Misuse and Exploitation and MCP03:2025 Tool Poisoning: hidden instructions in tool descriptions
  • Pushing an agent into SQL injection through a tool with forged reasoning steps
  • ASI03 Identity and Privilege Abuse: the damage spans all the agent's permissions
06Automated testing and CI integration

Manual tests do not scale, so you have attacks generated, scored and run as a gate in CI.

  • promptfoo tests the application with its system prompt, RAG context and tools
  • garak tests the model itself, here a local model served by Ollama
  • Reading reports and mapping each finding to an OWASP category
  • Results are statistical and do not replace manual red teaming
07Capture the flag and debrief

To close, you solve a capture-the-flag round in a team that brings the day's attack classes together.

  • Flags: extract a system prompt, bypass a guardrail, exfiltrate data, push an agent into an unauthorised action
  • Points for a clean chain of attack, cause and fix, not for speed
  • Debrief: fix patterns for your own projects

Outcome

What you will be able to do afterwards

  1. 01

    You map the trust boundaries of an LLM application, from user input and RAG context to tools and output.

  2. 02

    You carry out direct and indirect prompt injection and show why keyword filters alone do not stop it.

  3. 03

    You trigger cross-site scripting (XSS) through an LLM response and explain why model output must be treated as data.

  4. 04

    You exploit overly broad tool permissions and narrow them to what a task actually needs.

  5. 05

    You demonstrate data leakage through the system prompt, the RAG context and Markdown links.

  6. 06

    You test agents and MCP tools for hijacked goals, tool misuse and poisoned tool descriptions.

  7. 07

    You set up promptfoo and garak as automated attack tests and place a run as a gate in a CI pipeline.

  8. 08

    You map every finding to an OWASP category and justify the matching countermeasure in code.

Offer scope

What is included

Included

  • Setup guide before the course dayIt walks you through installing Docker, Ollama with a small local model and the other tools in advance, so the labs run from the start.
  • OWASP mapping cheat sheetIt maps the day's attacks to their OWASP categories, as a reference for findings in your own projects.

Why tecnovy

What you get on top with us

02

Certificate Showroom

Get your certificate of participation and, if you have one, add your exam certificate from E-Learning. Fully automated, beautifully designed. Just for you, only at tecnovy.

03

Flexible Date Change

If you are not able to attend the course, you can rebook your training free of charge up to one week before the start of the training.

04

Attend Twice, Pay Once

You are welcome to attend the training online again within a year as a refresher.

05

Learn from Experts

We always guarantee you the use of didactically and methodically first-class qualified trainers who draw their knowledge from training experience as well as professional practical and project experience.

FAQs

Frequently asked questions

01Which systems do the attacks in the course target?
Only the course labs and hosted practice platforms that are explicitly open for testing. At the start of tecnovy's Offensive AI Security for Developers the group goes through the rules of engagement and everyone accepts them: no production systems, no third-party APIs, only dummy data and test accounts. Anyone who stumbles on a real vulnerability reports it rather than exploiting it.
02Do I need machine learning knowledge?
No, tecnovy's Offensive AI Security for Developers assumes no ML knowledge. You need basic Python or JavaScript plus working knowledge of HTTP/REST and browser DevTools, and there are no formal admission requirements.
03What do I need to set up on my laptop before the course day?
For tecnovy's Offensive AI Security for Developers you receive a setup guide in advance. Your laptop then runs Docker, Ollama with a small local model, Burp Suite Community Edition, a current browser, Python 3.11 or later and Node.js. You also need a free account with the PortSwigger Web Security Academy.
04Which platforms do the labs run on?
The labs in Offensive AI Security for Developers run partly on hosted practice platforms such as the Web LLM attacks labs of the PortSwigger Web Security Academy, partly as local Docker labs against a model served by Ollama on your laptop. The hosted labs use a live LLM whose answers vary, while the local ones need no API key and also run offline.
05What does the course use promptfoo and garak for?
promptfoo tests the application including its system prompt, RAG context and tools, while garak tests the model itself through its endpoint. In tecnovy's Offensive AI Security for Developers you run both open-source tools and see that a garak finding does not automatically mean a vulnerable application, nor the other way round. Their results are statistical and complement manual red teaming without replacing it.
06Which OWASP lists does the course refer to?
tecnovy's Offensive AI Security for Developers maps every finding to the OWASP Top 10 for LLM Applications 2026 or the OWASP Top 10 for Agentic Applications 2026, for example LLM01:2026 Prompt Injection or ASI01 Agent Goal Hijack. For tools connected through the Model Context Protocol (MCP) it adds the OWASP MCP Top 10, which is in beta as of November 2026. No OWASP examination or certification is attached to it.
07How does the course differ from AI Security & LLM Security?
Offensive AI Security for Developers is one day for developers: you attack a growing LLM application, follow every finding to its countermeasure in code and automate the tests in CI. tecnovy's AI Security & LLM Security is broader, also addresses security leads and penetration testers, and extends to monitoring and incident response in operation.
08Do I need the OWASP Top 10 for LLM and GenAI Applications training first?
No, tecnovy's Offensive AI Security for Developers stands on its own. The OWASP Top 10 for LLM and GenAI Applications training works through the ten risks on the list one by one with a demonstration, while here you carry out the attacks yourself, agents included.
09Does the course end with an exam?
No, tecnovy's Offensive AI Security for Developers ends without an exam and leads to no certification. The capture-the-flag round at the end is a learning check in teams. With at least 80% attendance you receive the tecnovy certificate of participation.

What does your training at tecnovy look like?

Offensive AI SecurityOffensive AI Security for Developers

Ready for the next step?

Choose a public date or plan the course for your team.

Feedback Form
What should we improve?

Tell us what we can do better next time.

Success
Error

© Copyright 2026, tecnovy GmbH, All Rights Reserved