This repository was archived by the owner on Jun 5, 2025. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 82
Suspicious Command Detection #34
Labels
Comments
@lukehinds marked for roadmap planning |
I figure we need to do some re-planning around this work? I heard @jhrozek might believe some client work should land first? |
Note: #1151 landed. It is an open question if we want to disable again. |
Awaiting client work |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Uh oh!
There was an error while loading. Please reload this page.
Suspicious Command Detection
Summary
Introduce a mechanism to detect and flag potentially suspicious commands generated by AI assistants / agents. This feature will prompt the user to double-check such commands before they are executed or accepted, particularly for fully agentic workflows (where commands might be auto-run).
Background & Motivation
Requirements
curl | bash
nc -l
sudo
PATH
,LD_LIBRARY_PATH
, etc.)chown
,chmod
)npm install
, unless a positive vetting mechanism is in placerm -rf *
, fork-bomb:(){ :|:& };:
“Are you sure you want to run this command? It may have system-wide effects.”
Implementation Ideas
“Command flagged: curl | bash. Confirm to proceed or skip.”
Acceptance Criteria
Additional Notes
The text was updated successfully, but these errors were encountered: