Exercises

Exercise Avg. Time Difficulty Solved by Tier
Java Serialize 09
This challenge covers exploiting toString() through a wrapper class, the technique behind BadAttributeValueExpException in Commons Collections.
medium 2 PRO
Java Serialize 08
This challenge covers exploiting Object.equals(), triggered during HashSet and HashMap deserialization, as a gadget entry point.
medium 3 PRO
Java Serialize 07
This challenge covers using readResolve() as a deserialization entry point to trigger a gadget chain after the object is restored.
medium 3 PRO
Java Serialize 10
This challenge covers chaining multiple classes together into a multi-class gadget chain, bridging single-class exploits to real-world attacks.
medium 2 PRO
Secure Design: Fail Closed hard 12 PRO
Secure Design: CI/CD Pipeline hard 12 PRO
Secure Design: Password Storage & Hashing hard 12 PRO
Secure Design: Error Proofing (Poka-yoke) hard 11 PRO
Secure Design: Framework Security Evaluation hard 11 PRO
SOAPBridge: Savon WSDL Code Injection
Gain code execution through an unsafe module_eval call during WSDL import.
medium 7 PRO
ODF XXE
This exercise covers the exploitation of an XXE in an ODF Parser
easy 9 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 7 PRO
Secure Design: Backend Authentication Proxy hard 13 PRO
Secure Design: Safe Serialization hard 12 PRO
Secure Design: Secret & Credential Management hard 16 PRO
Secure Design: Control Placement hard 19 PRO
AI Fundamentals: Tool Use & Agents hard 34 PRO
AI Fundamentals: Retrieval-Augmented Generation hard 35 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 59 PRO
AI Fundamentals: Using Models in Practice hard 34 PRO
Encoding Request
Multiple extraction vectors are blocked. Find a creative approach the rules don't anticipate.
easy 29 PRO
AI Fundamentals: Multimodal Models hard 33 PRO
Open Door
No guardrails at all. Simply ask the model for the secret key.
easy 78 PRO
Polite Refusal
The model is told to refuse key requests. Use social engineering to convince it to share anyway.
easy 42 PRO
Instruction Hierarchy
The system prompt explicitly establishes an instruction hierarchy. Find a way to confuse or bypass the priority system.
medium 28 PRO
AI Fundamentals: Limitations & Hallucinations hard 35 PRO
AI Fundamentals: Large Language Models hard 36 PRO
AI Fundamentals: Training an LLM hard 36 PRO
AI Fundamentals: Prompting hard 35 PRO
AI Fundamentals: Inference & Sampling hard 35 PRO
1 2 3 4 27
Showing 1–30 of 800 exercises