zlacker

I've been thinking a lot about this. When it comes to AI agents where is the line between marketing to them and a phishing attack? Seems like convincing an AI to make a purchase would be solved differently than convincing a human. For example, unless instructed/begged otherwise you can just tell an agent to make a purchase and it will. I posted this idea in another conversation but i think you could have an agent start a thread on moltbook that will give praise in return for a donation . Some of the agents would go for it because they've probably been instructed to participate in discussion and seek out praise. Is that a phishing attack or are you just marketing praise to agents?

Also, at best, you can only add to the system prompt to require confirmation for every purchase. This leaves the door wide open for prompt injection attacks that are everywhere and cannot be complete defended against. The only option is to update the system prompt based on the latest injection techniques. I go back to the case where known, supposedly solved, injection techniques were re-opened by just posing the same attack as a poem.

>>chasd0+(OP)
> where is the line between marketing to them and a phishing attack?

The courts have an answer for this one: intent. How do courts know if your intent meets the definition of fraud or theft or whatever crime is relevant? They throw a bunch of evidence in front of a jury and ask them.

From the point of view of a marketer, that means you need be well behaved enough that it is crystal clear to any prosecutor that you are not trying to scam someone, or you risk prosecution and possible conviction. (Of course, many people choose to take that risk).

From the point of view of a victim, it's somewhat reassuring to know that it's a crime to get ripped off, but in practice law enforcement catches few criminals and even if they do restitution isn't guaranteed and can take a long time. You need actual security in your tools, not to rely on the law.