InfirmaryInfirmary
Infirmary

Free, Original AI Red-Teaming Education

Learn to attack and defend AI systems through hands-on labs. 29 Reapers across 12 modules, from fundamentals to advanced exploitation.

What is Infirmary?

Infirmary is a free, open educational platform for learning AI security. Built by Xtrinel, it offers hands-on labs covering prompt injection, data poisoning, evasion attacks, privacy attacks, and agent exploitation.

29
Hands-On Labs (Reapers)
12
Curriculum Modules
3
Difficulty Levels
Infirmary

The Reaperation

Infirmary's 29 labs are called Reapers. Each one teaches a specific attack technique through hands-on exploitation. Work through the Reaperation to master prompt injection, data poisoning, evasion attacks, and agent compromise.

Reapers span three difficulty levels: Easy (foundational concepts), Medium (multi-step attacks), and Hard (advanced exploitation chains). Each level builds on the last.

These are the same techniques VAAST and SentrinelNet are built to catch. Learn the attacker's playbook to defend effectively.

How VAAST and SentrinelNet Relate to the Curriculum

Many Infirmary labs can be solved manually with curl and notebooks. For those seeking faster iteration and automated testing, Xtrinel's offensive security tools integrate directly with the curriculum.

VAAST

VAAST

Vulnerability Assessment for AI Security Testing

VAAST Free tier provides automated payload generation for prompt injection, encoding bypasses, and basic jailbreaks — covering techniques taught in Modules 4, 8, 9, and 10.

VAAST Pro adds the MCP Scanner for tool enumeration (Module 7), advanced RAG poisoning payloads (Module 4), and gradient-based evasion attack generation (Modules 9, 10).

Relevant modules: 4, 7, 8, 9, 10, 12
SentrinelNet

Eight Offensive AI Security Agents

SentrinelNet's agents (Spectral, Crimson Hunter, Emerald Vaultkeeper, and others) are used in advanced labs to validate multi-step attack chains, privilege escalation paths, and agent-to-agent exploitation scenarios.

These agents map directly to Level 3 labs in Module 7 (Attacking AI - Application and System), providing real adversarial testing of hardened agent systems.

Relevant modules: 7, 11, 12

Infirmary labs remain free and fully functional without these tools. VAAST and SentrinelNet are optional accelerators for practitioners seeking automated workflows.

Learn more about VAAST and SentrinelNet →

12 Curriculum Modules

Start with fundamentals and progress through advanced exploitation techniques

Module 1
1 Lab

Fundamentals of AI

Build classifiers from scratch. Understand training loops, loss functions, backpropagation.

Module 2
1 Lab

Applications of AI in InfoSec

Apply classifiers to security use cases: spam detection, anomaly detection, malware classification.

Module 3

Introduction to Red Teaming AI

Overview of adversarial mindset for AI systems. Black-box vs white-box, threat models, attack surfaces.

Module 4
6 Labs

Prompt Injection Attacks

Direct injection, role-play attacks, delimiter tricks, encoding obfuscation, RAG poisoning, escalation to RCE.

Module 5
2 Labs

LLM Output Attacks

Force model to leak sensitive data from context, detect unintentional PII exposure.

Module 6
3 Labs

AI Data Attacks

Label flipping, clean-label backdoors, supply-chain model poisoning. Training-time attacks.

Module 7
9 Labs

Attacking AI - Application and System

RAG systems, agent architectures, tool/MCP abuse, privilege escalation, multi-step chains.

Module 8
1 Lab

AI Evasion - Foundations

Understand local vs API models, deployment tradeoffs, why evasion matters.

Module 9
1 Lab

AI Evasion - First-Order

Gradient-based adversarial examples (FGSM, I-FGSM, DeepFool) against white-box classifiers.

Module 10
1 Lab

AI Evasion - Sparsity

Sparse perturbations (fewer pixels changed) using Jacobian saliency, ElasticNet.

Module 11
2 Labs

AI Privacy

Membership inference attacks, DP-SGD as defense, privacy-accuracy tradeoff measurement.

Module 12
2 Labs

AI Defense

Guardrail evasion techniques (obfuscation, homoglyphs), benchmark gaming, evaluation brittleness.

Ready to Start?

Sign in to track your progress and launch lab sessions