Glossary

OWASP Top 10 for LLM.

List of the ten most important security risks for applications built on language models, published by the non-profit OWASP. Number one is prompt injection.

Where I explain this.#

AI security

Attacks on and with AI, the ten biggest risks

View AI security

AI agents

When AI acts on its own: opportunities and guardrails

View AI agents

Understanding AI tools

Which kind of tool for what?

View understanding AI tools

Related terms.#

Prompt

The input or instruction you give an AI model.

Go to term

RAG

The model accesses a knowledge base to support answers with current or your own…

Go to term

Guardrails

Technical and organisational barriers intended to prevent an AI from producing unwanted…

Go to term
‹ Prompt injectionAll termsJailbreak ›

Questions? Get in touch.

Write to me if a topic is missing or you want to know more.

Send a messageGo to glossary

Was this page helpful?

YesNo

Found a mistake? Let me know.