Whether or not prompt injection is genuinely harmful entirely depends on what developers build with this stuff.
If you're going to give a LLM-driven program the ability to execute functions that can change state in the world you need to understand prompt injection, so you don't accidentally build something that you really shouldn't have built.
If you're going to give a LLM-driven program the ability to execute functions that can change state in the world you need to understand prompt injection, so you don't accidentally build something that you really shouldn't have built.
The first public prompt injection vulnerability was a Twitter bot which started spam-mentioning people and threatening the president. https://arstechnica.com/information-technology/2022/09/twitt...