Launch HN: Slashy (YC S25) – AI that connects to apps and does tasks

Re:Launch HN: Slashy (YC S25) – AI that connects to apps and... by tehsuk on Thursday September 04, 2025 @03:03PM (#45130994)

Anything that gives any sort of system access to sensitive data and lets agents carry out actions on basically unchecked input sounds like a complete security and privacy nightmare by design.

[ Parent | on HN ]

Re:Launch HN: Slashy (YC S25) – AI that connects to apps and... by hgaddipa001 on Thursday September 04, 2025 @03:37PM (#45131366)

Why do you think privacy?

Security I understand, but if you consent to giving it access would it not be fine for privacy.

[ Parent | on HN ]

Re:Launch HN: Slashy (YC S25) – AI that connects to apps and... by brazukadev on Thursday September 04, 2025 @03:41PM (#45131413)

You give it access, it grabs your ssh keys and exfiltrate to some third party server. That is not the access the user gave to your platform but it is what it would be capable of doing.

[ Parent | on HN ]

Re:Launch HN: Slashy (YC S25) – AI that connects to apps and... by hgaddipa001 on Thursday September 04, 2025 @03:51PM (#45131522)

Ohh we don't give it computer use access or anything like that. We inject tokens post tool call, so to protect users from the agent doing anything malicious.

[ Parent | on HN ]

Re:Launch HN: Slashy (YC S25) – AI that connects to apps and... by tehsuk on Friday September 05, 2025 @12:08AM (#45134900)

I'm thinking about what this post explains more clearly than I can:

https://simonwillison.net/2025/Jun/16/the-lethal-trifecta

Seems to me that these kind of systems, by design, tick all three boxes. I've had many discussions with people that let agent systems read and act on their incoming email for instance, and I think it's utter insanity from a security perspective.

[ Parent | on HN ]