Agentic AI systems face a fundamental security flaw: LLMs cannot distinguish instructions from data, making them vulnerable to prompt injection attacks. The "Lethal Trifecta" occurs when an LLM has access to sensitive data, untrusted content, and external communication simultaneously, enabling attackers to exfiltrate
Table of contents
Minimising access to sensitive dataBlocking the ability to externally communicateLimiting access to untrusted contentBeware of anything that violate all three of these!Use sandboxingSplit the tasksKeep a human in the loop3 Comments
Sort: