What is prompt injection?
An attack that hides malicious instructions inside the input or data an AI reads, tricking it into acting outside its intended purpose. As in this case, an AI can sometimes generate this kind of instruction for itself.
Terms seen alongside this one
- misalignment 3× together
- open-weight model 3× together
- MCP 2× together
- SynthID 2× together
Get it in your inbox every day
Daily headlines and summaries, a weekly synthesis every Sunday, and a monthly report at the start of each month. Sent at 8AM KST, which is the evening before in the US.
Free · no ads · one-click unsubscribe