Repository navigation
It should be possible to configure a set of commands the agent can run without permission #2484
Closed as duplicate
Description
Describe the feature or problem you'd like to solve
No response
Proposed solution
Currently you can only set allow-all to allow the agent to execute commands without permission. Otherwise with every new session i have to approve every command over and over again.
The --allow-all flag bypasses all permission checks, which create real risks:
- Destructive commands like" rm-rf" could be e executed without confirmation
- Permission changes (chmod, chown) could silently alteer system security
A granular allowlist ( eg allow read, find, cat,ls but block rm, chmod, would provide a much better balance between autonomy and safety.
This should be configurable via instruction or agent files
Example prompts or workflows
No response
Additional context
No response
Activity
jamesdraughn commentedon Apr 3, 2026
I think the proposed feature should also include the ability to granularly remove permissions after allow-all.
alkutn123-tech commentedon Apr 3, 2026
السماح للجميع
alkutn123-tech commentedon Apr 3, 2026
السماح
cbruegg commentedon Apr 10, 2026
It would be great if Copilot CLI could reuse the VS Code settings for auto approvals (
chat.tools.terminal.autoApprove)schizek commentedon Apr 10, 2026
I absolutely agree, we need this feature. It is one of the main reasons I prefer using Warp or Claude for my terminal-based AI rather than Copilot CLI.
FWIW, this appears to be a duplicate of #1973
patniko commentedon Oct 26, 2026
Thanks for the report! This is the same issue as #1973, so I'm closing this one as a duplicate. Please follow that issue for updates and add any extra details there.
Triaged as part of a Copilot SDK backlog review, with help from GitHub Copilot.