Modified 2 August 2026

AI glossary

LLMjacking

An attack where adversaries steal an LLM API key and use it to run requests at the victim's expense. They don't steal data, they steal usage. A leaked Gemini key reportedly turned a ~$180/month bill into $82,314 in 48 hours. The risk grows as businesses embed language models into websites, apps, and internal tools: if a key leaks, the attacker doesn't need to access data, they just run usage on the account until the bill explodes.

Related terms

• API key
• Secret management
• .env file
• Data Exfiltration

Read more on Agentakademin

• Säkerhet