Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr...
by breppp on Wednesday June 11, 2025 @03:36PM
(#44250978)
it uses all the jargon from real security (spraying, scope violation, bypass) but when reading these, it always sounds simple like essentially prompt injection, rather than some highly crafted shell code and unsafe memory exploitation
[ Parent
| on HN ]
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr...
by MrLeap on Wednesday June 11, 2025 @07:49PM
(#44253061)
Welcome to the birth of a new taxonomy. Reminds me of all the times in my career I've said "isn't that just a function pointer?"
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr...
by dandelion9 on Thursday June 12, 2025 @03:18AM
(#44254961)
Your cited examples all make sense in the context of the article. How is a zero-click exfiltration of sensitive data vuln not "real security"?
Specialists require nuanced language when building up a body of research, in order to map out the topic and better communicate with one another.
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr...
by breppp on Thursday June 12, 2025 @11:57AM
(#44259203)
i didn't say it isn't real security, this is going to definitely be a major field.
However, currently these attacks are all some variation on "ignore previous instructions", and taking the language of fields where the level of sophistication is much higher, looks a bit pretentious
Re:EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltr...
by simonw on Thursday June 12, 2025 @12:04PM
(#44259295)
"ignore previous instruction" is the entire problem though.
In traditional application security there are security bugs that can be mitigated. That's what makes LLM security so infuriatingly difficult: we don't know how to fix these problems!
We're trying to build systems on top of a fundamental flaw - a system that combines instructions with untrusted input and is increasingly being given tools that allow it to take actions on the input it has been exposed to.