Skip to main content
GGenerative AI
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
SearchStart here
Menu
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
  1. Reference
  2. Lethal trifecta

Glossary

Lethal trifecta

The combination of private data, exposure to untrusted content and an outbound channel in one agent. Together they allow data theft, so do not combine all three.

Where it is explained

  • Limiting blast radius and treating output as untrustedSafety and guardrails

See also

Terms explained in the same lessons.

  • Excessive agency
  • Improper output handling
  • Least privilege
  • Blast radius
  • Human approval
  • System prompt
Previous termLeast privilegeNext termLLM

All terms, A to Z

GGenerative AI

Learn generative AI from the first token to production systems.

  • Privacy
  • Search