Glossary · Term

termination poisoning

← all terms

Definition

An attack that doesn't crash an AI agent but quietly keeps it from realizing it's done.

A class of indirect prompt-injection attacks targeting an LLM agent's stopping criterion, inflating step counts and inference cost without producing overt failure.

Mentioned in 1 episode

  1. 030
    Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap