Glossary · Phase 1 · Building with LLMs
Allowlist
A list of the only things permitted, such as the few web addresses an agent may contact. Anything not on it is blocked.
Learn it properly
Prompt injection and security · How untrusted text hijacks models, and how to limit the damage. About 30 minutes.
Other terms from the same lesson
- lethal trifecta: An agent that can read private data, also reads untrusted text, and can send data out. With all three, one hidden instruction can leak your data.
- prompt injection: An attack where text the model reads (a web page, an email) contains instructions that try to hijack it.