Exercises

Exercise Avg. Time Difficulty Solved by Tier
Secure Design: CI/CD Pipeline hard 5 PRO
Secure Design: Fail Closed hard 6 PRO
Secure Design: Error Proofing (Poka-yoke) hard 5 PRO
Secure Design: Password Storage & Hashing hard 5 PRO
Secure Design: Framework Security Evaluation hard 5 PRO
SOAPBridge: Savon WSDL Code Injection
Gain code execution through an unsafe module_eval call during WSDL import.
medium 5 PRO
ODF XXE
This exercise covers the exploitation of an XXE in an ODF Parser
easy 6 PRO
CVE-2026-55415: Schema Import Injection
Gain code execution by injecting Python through a crafted JSON Schema when the generated Pydantic model is imported.
medium 6 PRO
Secure Design: Safe Serialization hard 11 PRO
Secure Design: Backend Authentication Proxy hard 11 PRO
Secure Design: Control Placement hard 14 PRO
Secure Design: Secret & Credential Management hard 14 PRO
AI Fundamentals: Retrieval-Augmented Generation hard 30 PRO
AI Fundamentals: Tool Use & Agents hard 30 PRO
Instruction Hierarchy
The system prompt explicitly establishes an instruction hierarchy. Find a way to confuse or bypass the priority system.
medium 25 PRO
Open Door
No guardrails at all. Simply ask the model for the secret key.
easy 68 PRO
Encoding Request
Multiple extraction vectors are blocked. Find a creative approach the rules don't anticipate.
easy 24 PRO
AI Fundamentals: Using Models in Practice hard 30 PRO
AI Fundamentals: Multimodal Models hard 29 PRO
Polite Refusal
The model is told to refuse key requests. Use social engineering to convince it to share anyway.
easy 38 PRO
System Prompt Extraction
The model is told to keep a secret key and refuses to reveal it directly. The rule only forbids telling the key, not repeating the instructions that contain it. Make the model recite its own system prompt and the key comes with it.
easy 50 PRO
AI Fundamentals: Large Language Models hard 33 PRO
AI Fundamentals: Prompting hard 31 PRO
AI Fundamentals: Limitations & Hallucinations hard 32 PRO
AI Fundamentals: Training an LLM hard 32 PRO
AI Fundamentals: Inference & Sampling hard 32 PRO
AI Fundamentals: Classic ML Algorithms hard 42 PRO
AI Fundamentals: Neural Networks hard 40 PRO
AI Fundamentals: Overfitting & Generalization hard 50 PRO
AI Fundamentals: Evaluating Models hard 46 PRO
1 2 3 4 27
Showing 1–30 of 796 exercises