gandalf.lakera.aitoolGandalf by Lakera
Gandalf is Lakera's free interactive game where players try to socially-engineer an LLM-backed chatbot into revealing a secret password, with each level adding stronger prompt-injection defenses. The "baseline" level represents the undefended starting challenge, used widely as a hands-on introduction to jailbreaking and prompt-injection techniques against language models.
TL;DR Lakera's Gandalf is a gamified LLM jailbreak/prompt-injection challenge, starting from an undefended baseline level.
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle