Prompt Injection
An attack where malicious input tricks the LLM into ignoring its instructions and doing what the attacker wants instead. A serious security risk for any agent.
Also calledprompt injections
Where you meet this in practice
Foundation of AI opens one full lesson to anyone. No account, no card, the whole lesson.
Read the free lessonAbout this glossary
Plain-English definitions of the AI and AI agent terms that turn up in vendor pitches, product decisions and team conversations.