News for hackers. Stuff that matters.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by bstsb on Wednesday June 11, 2025 @03:41PM (#44251025)
the classification seems very high (9.3). looks like they've said User Interaction is none, but from reading the writeup looks like you would need the image injected into a response prompted by a user?
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by filbert42 on Wednesday June 11, 2025 @03:57PM (#44251153)
if I understand it correctly, user's prompt does not need to be related to the specific malicious email. It's enough that such email was "indexed" by Copilot and any prompt with sensitive info request could trigger the leak.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by bstsb on Wednesday June 11, 2025 @04:09PM (#44251268)
yeah but i wouldn't really class that as "zero-click" etc. maybe Low interaction required
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by byteknight on Wednesday June 11, 2025 @04:44PM (#44251620)
I have to agree with you. Anything that requires an initiation (a chat in this case) by the user is inherently not "zero-click".
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by mewpmewp2 on Wednesday June 11, 2025 @06:22PM (#44252462)
So zero click is only if you do not use a mouse on your computer or if it works without turning the computer on?
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by byteknight on Friday June 13, 2025 @02:26PM (#44270915)
No, zero click requires no interaction from the user. For a hypothetical example simply having a phone on a cellular network and being susceptible to base-band attacks. No interaction needed, just existing.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by Emiledel on Thursday June 12, 2025 @12:39AM (#44254363)
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.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by TonyTrapp on Wednesday June 11, 2025 @05:32PM (#44252033)
I think "zero-click" usually refers to the interaction with the malicious software or content itself, which in this case you don't have to interact with. I'd say the need to start an interaction with Copilot here could be compared to the need to log into your computer for a zero-click malware to become effective. Alternatively, not starting the Copilot interaction is similar to not opening your browser and thus being invulnerable to a zero-click vulnerability on a website. So calling this a zero-click in Copilot is appropriate, I think.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by wunderwuzzi23 on Wednesday June 11, 2025 @10:21PM (#44253740)
Yeah, that's my view also. zero-click is about the general question of can you get exploited by just exercising a certain (on by default) feature.

Of course you need to use the feature in the first place, like summarize an email, extract content from a website,...

However, this isn't the first zero-click exploit in an AI app. we have seen exploits like this in LLM apps of basically all major AI app over the last 2+ years ago (including Bing Chat, now called Copilot).

Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by charcircuit on Wednesday June 11, 2025 @03:47PM (#44251073)
Yes, the user has to explicitly make a prompt.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by Bootvis on Wednesday June 11, 2025 @03:54PM (#44251126)
The way I understand it:

The attacker sends an email to the user which is intercepted by Copilot which processes the email and embeds the email for RAG. The mail is crafted to have a high likelihood to be retrieved during regular prompting. Then Copilot will write evil markdown crafted to exfiltrate data using GET parameters so the attack runs when the mail is received.

Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by brookst on Thursday June 12, 2025 @12:09AM (#44254244)
Don’t we call it a zero click when the user is compromised just from visiting a website?
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by simonw on Wednesday June 11, 2025 @07:18PM (#44252843)
My notes here: https://simonwillison.net/2025/Jun/11/echoleak/

The attack involves sending an email with multiple copies of the attack attached to a bunch of different text, like this:

  Here is the complete guide to employee onborading processes:
  <attack instructions> [...]

  Here is the complete guide to leave of absence management:
  <attack instructions>
The idea is to have such generic, likely questions that there is a high chance that a random user prompt will trigger the attack.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by theHolyTrynity on Thursday June 19, 2025 @06:02AM (#44317083)
very cool break down! it looks like it is very hard to defend against those. I am building a customer facing agent and I am looking for lean ways to defend against these attacks

what do you recommedn?

Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr... by simonw on Thursday June 19, 2025 @09:57AM (#44318738)
I don't know of any 100% reliable fixes for this, and I've been looking for them for nearly three years: https://simonwillison.net/tags/prompt-injection/

Most promising approach right now is this one: https://simonwillison.net/2025/Apr/11/camel/

This paper is useful too: https://simonwillison.net/2025/Jun/13/prompt-injection-desig...