Data Exfiltration from Slack AI via indirect prompt injection

from PromptArmor Blog [alt+shift+b] in AI

Authors: PromptArmor

6 months ago

Remove from reading list Add to reading list [alt+a] Read now [→]

Improve your reading experience

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from PromptArmor Blog

Slack AI data exfiltration from private channels via indirect prompt injection

Authors: PromptArmor

6 months ago • 22 votes

Announcing LASEC: LLM Application Security Executive Certification

Including a never before seen exploit from PromptArmor's cutting edge threat intelligence team.

11 months ago • 22 votes

Data exfiltration from Writer.com with indirect prompt injection

Authors: PromptArmor and Kai Greshake

a year ago • 17 votes

Coming soon

This is PromptArmor Blog.

a year ago • 15 votes

More in AI

Speaking things into existence

Expertise in a vibe-filled world of work

9 hours ago • 2 votes

Response to Scott Alexander on Imprisonment

Back in November 2024, Scott Alexander asked: Do longer prison sentences reduce crime?

7 hours ago • 1 votes

Don’t think of a basketball player, or search engines don’t even support “not”

In my opinion we have been accepting poor interfaces and results from search engines for quite a while. This may be a small part of why the newer Large Language Models (LLMs) / Generative AIs look so good. The large language models at least implement a usable approximation of what […]

2 days ago • 4 votes

The Manus Marketing Madness

While at core there is ‘not much to see,’ it is, in two ways, a sign of things to come.

2 days ago • 2 votes

Urgent warning: Black Mirror has entered the United States, with AI as its handmaiden

AI as a smoke screen to cover for authoritarian actions

2 days ago • 2 votes

New here?