2-Day Course · Hands-on
Intermediate · 2-Day

LLM Application Security for Developers

Build LLM features that survive security review, using the OWASP LLM Top 10 and hands-on guardrails, in two days.

Code DEV-521 Format 2 days, hands-on Level Intermediate
Secure Build Guardrails LLM Top 10
Grounded in the standards

Built on the OWASP LLM Top 10

You work through the OWASP Top 10 for LLM applications with live examples, then build the input and output guardrails that hold those risks down in real code. The course counts toward the CyberSecAI AISVS assurance track and is taught by the former OWASP-AISVS Co-Leader (v1.0).

You will be able to

What you can do after the course

DEV-521. The syllabus

LLM Application Security for Developers

Two-day instructor-led course. Module order and grouping can be adjusted for private deliveries.

Secure AI Development Fundamentals

The ground rules for LLM integration

130-00 The OWASP LLM Top 10 in Code 1.5 hr

Walking through the OWASP LLM Top 10 with live code examples so you see what each risk looks like in a running application. Each risk is mapped to the matching AISVS control so you leave with a checklist tied to a recognised standard, not a list of slogans.

130-01 Secure-by-Default Patterns for LLM Integration 1 hr

The patterns that make an LLM integration secure from the start. You study parameterised prompts, input validation, output encoding and fail-closed defaults so security is built into the design rather than bolted on after.

130-02 The Trust Boundary Between Application and Model 1 hr

Where the trust boundary sits between your application code and the model. You map the point where your application hands data to the model and where it receives output back, and you treat both crossings as untrusted by default.

130-03 Model Output as Untrusted Input 1 hr

Treating everything the model returns as untrusted input to your application. You study why model output can contain injection payloads, hallucinated data and unsafe content, and you build the habit of validating and encoding every response before your application acts on it.

Input Handling and Prompt Construction

Building prompts that resist injection

131-00 Parameterised Prompts 1.5 hr

Applying the SQL injection lesson to LLMs. You build parameterised prompt templates where user input is data, never part of the instruction, so an injected instruction cannot change what the model is told to do. You test each template against known injection patterns.

131-01 Input Validation and Sanitisation 1 hr

Validating and sanitising user input before it reaches the model. You set up validation rules that reject obviously malicious input, strip control characters and encoding tricks, and enforce length limits so oversized payloads never enter the prompt.

131-02 System Prompt Design That Resists Injection 1 hr

Writing system prompts that are harder to override. You study how instruction hierarchy works, write system prompts with clear boundaries, and test them against override attempts so the model follows your instructions, not the attacker's.

131-03 User Input Isolation 1 hr

Isolating user input from system instructions in the prompt. You use delimiters, role separation and structured templates to keep user-supplied text in a clearly marked data zone where the model treats it as content, not as a command.

Output Handling and Safety

Making model output safe for your application

132-00 Treating Model Output as Untrusted 1 hr

The discipline of never trusting model output. You build output processing pipelines that validate, sanitise and encode every response before it reaches the user or triggers any downstream action in your application.

132-01 Output Validation and Encoding 1 hr

Validating model output against expected schemas and encoding it for the context where it will be used. You write validators that reject malformed responses and encoders that prevent model output from being interpreted as HTML, JavaScript or SQL in your application.

132-02 Preventing XSS and Injection Through Model Responses 1 hr

Stopping cross-site scripting and injection attacks that arrive through model responses. You study how a model can be tricked into generating payloads, and you build output encoding and content security policies that neutralise those payloads before they execute.

132-03 PII and Sensitive Data Filtering on Output 1 hr

Filtering personally identifiable information and sensitive data from model output before it reaches the user. You configure output scanners that detect and redact PII patterns, credentials and internal data that the model should never surface in a response.

Guardrails in Your Stack

Deploying and testing guardrails

133-00 Deploying Input and Output Guardrails 1.5 hr

Setting up LLM Guard, Presidio and NeMo Guardrails in your application. You install each tool, configure it for your use case and wire it into the request and response pipeline so every prompt and every response passes through a guardrail before it continues.

133-01 Configuring Content Policies 1 hr

Writing content policies that define what your guardrails allow and block. You set up topic restrictions, toxicity thresholds and custom rules, then test them against a range of inputs to tune the policy until it matches your requirements.

133-02 Testing Guardrails in CI/CD 1 hr

Running guardrail tests as part of your continuous integration pipeline. You write test cases that exercise each guardrail rule, wire them into your CI system and configure the build to fail when a guardrail regression is detected.

133-03 The False Positive Tradeoff 1 hr

Understanding and managing the tradeoff between blocking harmful content and blocking legitimate requests. You measure false positive rates for each guardrail rule, adjust thresholds based on real traffic patterns and decide where your application can afford to be strict and where it needs to be lenient.

Tool Use and Agent Safety

Securing function calling and tools

134-00 Securing Function Calling and Tool Use 1.5 hr

How function calling works and where it goes wrong. You study the flow from model decision through function selection to execution, identify the trust assumptions at each step, and build controls that prevent the model from calling functions it should not or passing arguments that are dangerous.

134-01 Least-Privilege Tool Access 1 hr

Giving each tool only the permissions it needs and nothing more. You configure tool-level access controls, scope each tool's authority to the minimum required and test that a compromised tool call cannot escalate beyond its granted permissions.

134-02 Validating Tool Parameters Before Execution 1 hr

Checking every tool parameter against a schema before the function runs. You write parameter validators that reject unexpected types, out-of-range values and injection payloads so a malicious tool call is caught before it executes, not after.

Labs

Hands-on integration and guardrail labs

135-00 Secure LLM Integration Lab 2 hr

A structured lab where you build a secure LLM integration from scratch. You implement parameterised prompts, input validation, output encoding and PII filtering, then test the integration against injection attempts and verify that every control holds.

135-01 Guardrail Deployment Lab 2 hr

A hands-on lab where you deploy and configure guardrails in a running application. You set up LLM Guard and Presidio, write content policies, wire the guardrails into CI and measure false positive rates against a test suite of legitimate and malicious inputs.

135-02 Tool Safety Lab 1.5 hr

A lab focused on securing function calling and tool use. You configure least-privilege tool access, write parameter validators and test the controls against tool abuse scenarios where the model tries to call restricted functions or pass dangerous arguments.

~26 hrs
Total instructional hours
22
Individual modules
1-3 days
Flexible delivery
Tools and labs

Tools and labs you will use

Hands-on with the CyberSecAI tooling, not slideware.

mcps-fix

A security gate that checks AI-generated code at the moment it is written.

GuardBench

Guardrail effectiveness scorer (bypass rate and false-block rate).

Claw

The OWASP-standards scanner run in your CI pipeline.

AgentPass Ledger

Signed record of the security checks that ran on each build.

Who it is for

Built for the people shipping LLM features

Application developers

Add LLM features to a product without opening a hole in it.

ML and platform engineers

Stand up model and retrieval infrastructure that holds under attack.

AppSec engineers

Bring the LLM Top 10 and guardrails into your review remit.

Tech leads shipping LLM features

Set the bar your team ships to, and know it will pass review.

The certification

Counts toward the AISVS assurance track

This course counts toward the CyberSecAI AISVS assurance track. Assessment is practical: you build an LLM feature, separate its trust tiers, add input and output guardrails, secure the retrieval path, and wire the LLM Top 10 tests into CI.

Reserve a place

Ship LLM features you can defend.

Two days, hands-on, working the OWASP LLM Top 10 and building real guardrails, taught by the former OWASP-AISVS Co-Leader (v1.0). Places are limited.

2 days intensive, hands-on Hands-on guardrail labs Private corporate cohorts available
Reserve a Place

Corporate & sovereign cohorts, and bespoke on-site delivery, on request.