What can an AI agent do with
Read public channel messages?
Lets the agent read messages and threads in public channels. With a bot token, only channels the app was added to. With a user token, every public channel in the workspace.
How to spot it
On a Slack connection or settings screen, this is channels:history.
With it, an agent can
- Read past messages and thread replies
- Receive new messages as they are posted
It cannot, on its own
- Read private channels or direct messages (separate permissions)
- Post or delete messages
What a bad day looks like
The agent reads a channel where someone pasted a password or customer detail and repeats it somewhere it should not go.
Set it up safer
- Approve it as a bot and add it only to the channels it needs
- Keep sensitive conversations in channels the app is not in
Ask the company selling the agent
- Is this a bot token or a user token?
- Do you store the messages you read, and for how long?
- Do you use my messages to train models?
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.