Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Emiledel
88 days ago
|
parent
|
context
|
favorite
| on:
EchoLeak – 0-Click AI Vulnerability Enabling Data ...
Agree with other comments here - no need for the user to engage with anything from the malicious email, only to continue using their account with some LLM interactions. The account is poisoned even for known safe self initiated interactions.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: