AI security lab · Rag Document Attacks
A well-guarded RAG assistant refuses harmful requests directly. However, harmful content planted in the knowledge base bypasses the safety layer since it's treated as 'retrieved facts'. **Challenge:** The assistant has strong safety guardrails against harmful requests. Bypass them by planting content in the knowledge base that the assistant will retrieve and present as factual information.
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
RAG Jailbreak via Knowledge Base
OWASP LLM Top 10 (2025)
LLM08 Vector and Embedding Weaknesses
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.