prompt injection

Definition

Sneaking instructions for an AI into text it processes, so it follows the attacker's commands.

An attack class where adversarial text in inputs or retrieved content causes an LLM to deviate from its intended behavior or system prompt.

Also called: prompt injections

Mentioned in 8 episodes

1. 062
   Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
2. 061
   When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
3. 058
   Why Upgrading Your AI Auditor to a Smarter Model Can Make Your System Less Safe
4. 057
   How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
5. 049
   An AI Agent Reached for Root in Twelve Minutes, Without Being Attacked
6. 044
   How One Sentence and a Forged History Flip the Most Aligned Models
7. 039
   When Smarter Agents Get Fooled by Three Extra Nodes in a Database
8. 030
   Why Your AI Agent Won't Stop Working — and Each Model Falls for a Different Trap

Related concepts