Jailbreak
Tricking a model into bypassing its safety rules. A reputational risk for chatbots, a real one for agents with tools.
01In short
Tricking a model into bypassing its safety rules. A reputational risk for chatbots, a real one for agents with tools.
02Video
slot · videoJailbreak in 90 secondsadd: GUIDES['jailbreak'].video
03Guide
slot · guide
A step-by-step guide for “Jailbreak” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “Jailbreak”.
06Related terms
SecurityPrompt injectionInput crafted to make a model ignore its instructions — “ignore previous instructions and …”. Ranked the top risk in the OWASP Top 10 for LLM applications.SecurityRed teamingAttacking your own AI system on purpose — injections, jailbreaks, data leaks — before someone else does.
Where we help · Secure