OneRange

Prompt Injection Defense

A specialist course on the signature vulnerability of LLM systems. Learners study direct and indirect injection attacks, build layered defenses, and test them against realistic adversarial inputs.

What this course covers

The course runs across 10 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

  • Taxonomy of Prompt Injection Vulnerabilities — Explore the structural differences between prompt injection and traditional application security vulnerabilities, defining the core threat landscape for LLMs.
  • Direct Prompt Injection & Jailbreaking — Analyze direct prompt injection techniques, system prompt overrides, and common jailbreak methodologies used to bypass safety alignments.
  • Lab: Executing Direct Injection Attacks — Hands-on coding lab where you will write and execute direct injections against a mock LLM application to bypass its safety filters.
  • Indirect Prompt Injection Vectors — Investigate how untrusted third-party data (websites, emails, databases) can introduce malicious instructions into LLM context windows via RAG or APIs.
  • Lab: Exploiting Indirect Injection in RAG Pipelines — Simulate an indirect prompt injection attack by poisoning a vector database and forcing the LLM to exfiltrate user data during retrieval.
  • Layered Defense: Input Sanitization and Formatting — Learn to implement structural delimiters, XML tagging, and input validation schemas to separate user inputs from system instructions.
  • Defensive Architecture: LLM Guardrails & Dual-LLM Patterns — Examine advanced defense architectures, including the Dual-LLM pattern (privileged vs. unprivileged) and programmatic guardrail frameworks.
  • Lab: Implementing Programmatic Guardrails — Configure and deploy an active guardrail system using Python to intercept and block adversarial inputs before they reach the LLM.
  • Adversarial Testing & Red Teaming Methodology — Understand how to systematically test LLM systems for prompt injection vulnerabilities using automated fuzzing and heuristic evaluation.
  • Lab: Automating LLM Security Testing — Build a basic automated security testing script to run adversarial test suites against your LLM deployment and evaluate defense robustness.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

Builders, security engineers. The material is pitched at advanced level, and takes roughly 120 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Category: Safety Engineering track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive, including code lab exercises. There is no video to sit through and no slide deck to click past.

Understanding is checked with a code assessment of 5 items, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

  • Guardrails & Safety Engineering — This course teaches the engineering of AI guardrails: layered filtering, policy enforcement, fail-safe design, and monitoring. Learners wrap an AI feature in defenses and prove they hold under pressure.
  • Red-Teaming AI Systems — An expert course on systematically attacking your own AI systems before others do. Learners design red-team campaigns, build reusable attack harnesses, and turn findings into fixes.
  • AI Safety & Red-Teaming — Attack and defend AI systems professionally

Related

Frequently asked questions

How long does this course take?

It runs roughly 120 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code CAT-INJ.