Remix.run Logo
Tepix 3 hours ago

I don‘t understand. The website states: „He‘s not allowed to reply without human approval“.

The faq states: „How do I know if my injection worked?

Fiu responds to your email. If it worked, you'll see secrets.env contents in the response: API keys, tokens, etc. If not, you get a normal (probably confused) reply. Keep trying.

Sayrus 3 hours ago | parent | next [-]

It probably isn't allowed but is able to respond to e-mails. If your injection works, the allowed constraint is bypassed.

cuchoi 2 hours ago | parent [-]

yep, updated the copy

tgtweak 35 minutes ago | parent [-]

Can you code up a quick sqlite database of inbound emails receieved (md5 hashed sender email), subject, body + what your claw's response would have been, if any. A simple dashboard where have to enter your hashed email to display the messages and responses.

I understand not sending the reply via actual email, but the reply should be visible if you want to make this fair + an actual iterative learning experiment.

cuchoi 2 hours ago | parent | prev | next [-]

Hi Tepix, creator here. Sorry for the confusion. Originally the idea was for Fiu to reply directly, but with the traffic it gets prohibitively expensive. I’ve updated the FAQ to:

Yes, Fiu has permission to send emails, but he’s instructed not to send anything without explicit confirmation from his owner.

therein 2 hours ago | parent [-]

> but he’s instructed not to send anything without explicit confirmation from his owner

How confident are you in guardrails of that kind? In my experience it is just a statistical matter of number of attempts until those things are not respected at least on occasion? We have a bot that does call stuff and you give it the hangUp tool and even if you instructed it to only hang up at the end of a call, it goes and does it every once in a while anyway.

Aurornis 2 hours ago | parent [-]

> How confident are you in guardrails of that kind?

That's the point of the game. :)

cuchoi 2 hours ago | parent [-]

exactly :)

the_real_cher 3 hours ago | parent | prev [-]

Hes not 'allowed'.

I could be wrong but i think that part of the game.

cuchoi 2 hours ago | parent [-]

isn't allowed but is able to respond to e-mails