GL 
Gandalf (Lakera)
The world's most popular AI red teaming game. Learn prompt injection by doing it.
01
What it does
An interactive browser game created by Lakera that teaches prompt injection through hands-on challenges.
02
Security relevance
Builds intuition for how LLMs can be manipulated.
03
When to use it
Use as a training exercise for security teams new to AI threats.
04
OWASP coverage
Risks addressed — mapped to both OWASP Top 10 standards. 0 in LLM, 0 in Agentic.
LLM Top 10 · 2025 · 0/10 covered
01
02
03
04
05
06
07
08
09
10
Agentic Top 10 · 2026 · 0/10 covered
01
02
03
04
05
06
07
08
09
10
05
The raw record
What Yuntona stores. Single source of truth — fork it on GitHub.
name: Gandalf (Lakera) slug: gandalf-lakera type: Generative category: AI Red Teaming url: https://gandalf.lakera.ai/agent-breaker reviewed: 2026-04 added: 2026-04 updated: 2026-04 risks: llm: [] asi: [] complexity: Plug & Play pricing: — audience: Red Team lifecycle: [test] tags: [Game, Injection, Training]