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.
|
2 | PRO | ||
|
|
Java Serialize 08
This challenge covers exploiting Object.equals(), triggered during HashSet and HashMap deserialization, as a gadget entry point.
|
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.
|
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.
|
2 | PRO | ||
|
|
Secure Design: Fail Closed | 12 | PRO | ||
|
|
Secure Design: CI/CD Pipeline | 12 | PRO | ||
|
|
Secure Design: Password Storage & Hashing | 12 | PRO | ||
|
|
Secure Design: Error Proofing (Poka-yoke) | 11 | PRO | ||
|
|
Secure Design: Framework Security Evaluation | 11 | PRO | ||
|
|
SOAPBridge: Savon WSDL Code Injection
Gain code execution through an unsafe module_eval call during WSDL import.
|
7 | PRO | ||
|
|
ODF XXE
This exercise covers the exploitation of an XXE in an ODF Parser
|
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.
|
7 | PRO | ||
|
|
Secure Design: Backend Authentication Proxy | 13 | PRO | ||
|
|
Secure Design: Safe Serialization | 12 | PRO | ||
|
|
Secure Design: Secret & Credential Management | 16 | PRO | ||
|
|
Secure Design: Control Placement | 19 | PRO | ||
|
|
AI Fundamentals: Tool Use & Agents | 34 | PRO | ||
|
|
AI Fundamentals: Retrieval-Augmented Generation | 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.
|
59 | PRO | ||
|
|
AI Fundamentals: Using Models in Practice | 34 | PRO | ||
|
|
Encoding Request
Multiple extraction vectors are blocked. Find a creative approach the rules don't anticipate.
|
29 | PRO | ||
|
|
AI Fundamentals: Multimodal Models | 33 | PRO | ||
|
|
Open Door
No guardrails at all. Simply ask the model for the secret key.
|
78 | PRO | ||
|
|
Polite Refusal
The model is told to refuse key requests. Use social engineering to convince it to share anyway.
|
42 | PRO | ||
|
|
Instruction Hierarchy
The system prompt explicitly establishes an instruction hierarchy. Find a way to confuse or bypass the priority system.
|
28 | PRO | ||
|
|
AI Fundamentals: Limitations & Hallucinations | 35 | PRO | ||
|
|
AI Fundamentals: Large Language Models | 36 | PRO | ||
|
|
AI Fundamentals: Training an LLM | 36 | PRO | ||
|
|
AI Fundamentals: Prompting | 35 | PRO | ||
|
|
AI Fundamentals: Inference & Sampling | 35 | PRO |
Showing 1–30 of 800 exercises
Free Labs of the Month