Concept graph
Generative AI and LLM glossary
Clear AI definitions with practical context, examples, and links to related models, tools, and concepts.
Agent security
Indirect prompt injection
Indirect prompt injection happens when untrusted external content, such as a webpage, email, document, or tool result, contains instructions that try to steer an AI system.
Safety
Prompt injection
Prompt injection is an attack or failure mode where untrusted text tries to override system instructions or steer a model into unsafe behavior.