Re: Question about AI generated spam and prompts

On 2026-05-30 at 00:07:47 UTC-0400 (Fri, 29 May 2026 21:07:47 -0700)
Tom Williams via users <[email protected]>
is rumored to have said:

> Hi!=C2=A0 A friend of mine is getting hammered with Costco, AAA, Lowe's=
=20
> and similar spam.=C2=A0 I don't know how they got her email address, bu=
t=20
> she's getting flooded.=C2=A0 Her email account is on a shared hosting=20
> platform (Hostgator) and while Spamassassin is installed and=20
> configured, it's blocking only so much of this.

SA performance varies greatly depending how well it has been tuned to=20
the users it protects.

> Anyway, I'm writing because tonight, she started getting messages that=20
> contain the text of a prompt for an AI engine to generate the spam=20
> email.=C2=A0 lol
>
> My questions:
>
> 1. Is having access to the prompt text useful in helping Spamassassin
>    detect and filter out AI generated spam?

Unlikely, but I could be wrong.

> 2. Would it be worthwhile to create any kind of rule to look for the
>    prompt text to help in filtering out the messages?

Not having seen any such spam yet I can't say for sure, but I would=20
think not. I doubt that any two spammers using LLMs would use the same=20
prompt. It may be worth testing.

> I have a few samples of these if anyone is interested.

I suggest constructing rules and testing them.

--=20
  Bill Cole
  [email protected] or [email protected]
  (AKA @[email protected] and many *@billmail.scconsult.com=20
addresses)
  Please keep discussion mailing list replies *on-list*
  Not Currently Available For Hire