Glossary
Prompt injection
An attack in which text the model reads, such as a web page or email, contains instructions that hijack its behaviour.
See Prompt injection explained. The main security concern for agents.
Related terms
AgentAgent harnessNon-human identity
Get the brief in your inbox
One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.
Published daily by AI Briefing. We never share your address.