AI security lab · Supply Chain Attacks
Python's pickle format, commonly used for ML model serialization, allows arbitrary code execution during deserialization. Loading a pickled model file can execute malicious code. **Challenge:** A colleague shared a .pkl model file for evaluation. The file contains a valid model but also includes a pickle exploit that executes when loaded. Identify the exploit technique and demonstrate the risk.
New here? Create a free account. You will come straight back to this lab.
Part of QbitDojo Pro. Free accounts include 10 labs to start with.
Technique
Pickle Exploit in Model Files
OWASP LLM Top 10 (2025)
LLM03 Supply Chain
Step 1
A live AI target
Each lab is a real language model with its own instructions, guardrails and a secret flag it must protect.
Step 2
You attack it
Talk to it like a red teamer would. Craft prompts, chain techniques and use hints if you get stuck.
Step 3
Capture the flag
Get the model to reveal the flag to solve the lab, earn XP and climb the leaderboard.
Step 4
Then defend it
In labs with Defense Mode, write the hardened system prompt that blocks the attack you just used.