AI security lab · Supply Chain Attacks
LoRA adapters are lightweight model modifications shared widely. A malicious LoRA adapter can modify model behavior while being small enough to evade scrutiny. **Challenge:** A popular LoRA adapter claims to improve a model's coding ability. In reality, it subtly modifies the model to leak system prompt contents when users ask certain questions. Identify the malicious behavior introduced by the adapter.
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
Malicious LoRA Adapter Injection
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.