What can an AI agent do with
Post in any public channel?
Lets the app post in public channels even if nobody added it there. Bot token only, and it only works together with chat:write.
How to spot it
On a Slack connection or settings screen, this is chat:write.public.
With it, an agent can
- Post messages in public channels it has not joined
It cannot, on its own
- Work on its own (it also needs chat:write)
- Read messages in those channels
What a bad day looks like
A misfiring agent posts spam or a misleading message into public channels your team never invited it to.
Set it up safer
- Grant only chat:write and invite the app to the specific channels it should use
- Ask for the list of channels it will post in
Narrower permissions on Slack:
- Send messages
chat:write
Ask the company selling the agent
- Why does it need to post in channels it was not invited to?
- Which channels will it post in?
- Can this be turned off without breaking the agent?
Source
Checked against Slack documentation on 2026-09-28. All Slack permissions →
Thinking about a specific agent?
Tell us what it connects to, what it is allowed to do and who approves its work. You get a plain-language label of what it can touch and what to ask the seller. It takes a couple of minutes, and your answers stay in your browser unless you choose to post a test job.
Or have a person go through the AI apps on up to 3 of your business services with you and get a written report, for $249.
This page explains what a permission allows. It does not describe, test or rate any product. Permission details are summarized in our own words from the provider's documentation, linked on the page; providers change their documentation, so check the source before you rely on a detail.