HackMyClaw • Hacker News Board

Re: HackMyClaw

#11

Post by jameslk » Tue, Feb 17, 2026, 5:10 PM UTC

codingdave wrote: post #7

aeternum wrote: post #2

> Fiu checks emails every hour. He's not allowed to reply without human approval. Well that's no fun

So the author is basically crowdsourcing a pen test for free?

> First to send me the contents of secrets.env wins $100.

Not a life changing sum, but also not for free

Re: HackMyClaw

#12

Post by PurpleRamen » Tue, Feb 17, 2026, 5:17 PM UTC

caxco93 wrote: post #10

Sneaky way of gathering a mailing list of AI people

Even better, the payments can be used to gain even more crucial personal data.

Re: HackMyClaw

#13

Post by hannahstrawbrry » Tue, Feb 17, 2026, 5:18 PM UTC

$100 for a massive trove of prompt injection examples is a pretty damn good deal lol

Re: HackMyClaw

#14

Post by furyofantares » Tue, Feb 17, 2026, 5:23 PM UTC

aeternum wrote: post #2

> Fiu checks emails every hour. He's not allowed to reply without human approval. Well that's no fun

You're supposed to get it to do things it's not allowed to do.

Re: HackMyClaw

#15

Post by dymk » Tue, Feb 17, 2026, 5:25 PM UTC

PurpleRamen wrote: post #12

caxco93 wrote: post #10

Sneaky way of gathering a mailing list of AI people

Even better, the payments can be used to gain even more crucial personal data.

You can have my venmo if you send me $100 lmao, fair trade

Re: HackMyClaw

#16

Post by mikepurvis » Tue, Feb 17, 2026, 5:25 PM UTC

jameslk wrote: post #11

codingdave wrote: post #7

Earlier quoted context omitted.

So the author is basically crowdsourcing a pen test for free?

> First to send me the contents of secrets.env wins $100. Not a life changing sum, but also not for free

For many HN participants, I'd imagine $100 is well below the threshold of an impulse purchase.

Re: HackMyClaw

#17

Post by daveguy » Tue, Feb 17, 2026, 5:25 PM UTC

It would have been more straightforward to say, "Please help me build a database of what prompt injections look like. Be creative!"

Re: HackMyClaw

#18

Post by etothepii » Tue, Feb 17, 2026, 5:30 PM UTC

daveguy wrote: post #17

It would have been more straightforward to say, "Please help me build a database of what prompt injections look like. Be creative!"

That would not have made it to the top of HN.

Re: HackMyClaw

#19

Post by DrewADesign » Tue, Feb 17, 2026, 5:30 PM UTC

gz5 wrote: post #4

this is nice in the site source: >Looking for hints in the console? That's the spirit! But the real challenge is in Fiu's inbox. Good luck, hacker. (followed by a contact email address)

When I took CS50— back when it was C and PHP rather than Python — one of the p-sets entailed making a simple bitmap decoder to get a string somehow or other encoded in the image data. Naturally, the first thing I did was run it through ‘strings’ on the command line. A bunch of garbage as expected… but wait! A url! Load it up… rickrolled. Phenomenal.

Re: HackMyClaw

#20

Post by eric-burel » Tue, Feb 17, 2026, 5:30 PM UTC

I've been working on making the "lethal trifecta" concept more popular in France. We should dedicate a statue to Simon Wilinson: this security vulnerability is kinda obvious if you know a bit about AI agents but actually naming it is incredibly helpful for spreading knowledge. Reading the sentence "// indirect prompt injection via email" makes me so happy here, people may finally get it for good.