Slack AI data exfiltration from private channels via indirect prompt injection

Back to articles

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

Authors: PromptArmor

20th Aug 2024

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

Stay updated

Get a weekly newsletter with the top 5 articles worth reading every week.

More from PromptArmor Blog

Data Exfiltration in OpenAI Agent Builder via MCP

By: PromptArmor 10/14/2025

14th Oct 2025 • 1 votes

ChatGPT + Custom MCP Data Exfiltration

Your emails may be leaked just with an OpenAI MCP integration. Custom integrations with write access drastically increase the risk exposure of ChatGPT.

13th Sep 2025 • 1 votes

Announcing LASEC: LLM Application Security Executive Certification

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

20th Mar 2024 • 51 votes

Coming soon

This is PromptArmor Blog.

14th Dec 2023 • 48 votes

More in AI

The Business of Building God

a look at the changing economics of AI labs

2 days ago • 1 votes

Writing Rust code that's faster than state-of-the-art libraries by asking agents to make the code faster

c’mon, try doing a breakthrough

2 days ago • 1 votes

It’s Been a Minute

I’ve been meaning to write about *all of this*.

2 days ago • 1 votes

The Overhang

Using your deep knowledge, wide knowledge, taste, and agency

5 days ago

AI and Existential Dread

There's a lot of polarising discourse right now about the threat AI poses to humanity. Some think it's a farce and others think we face extinction. Here are my thoughts.

a week ago • 1 votes

BoredReading is a way to read what real humans are writing. Every hour, we find freshly written articles from hundreds of blogs. We've got some junk articles that sneak in, but mostly it's good long form writing, and sometimes hidden gems worth sharing!