Skip to content

open-coder-ai/rtk-dangerous-actions-blocker

v0.3.2Apache-2.0

Deprecated: use block-destructive-commands, which shares this policy's destructive-command table. rtk#1007. Same table as block-destructive-commands: blocks root/home/.git deletes, force/delete/mirror pushes, reset --hard, clean -f, switch --discard, IaC destroy, cloud deletes, DB drops, lockouts; asks rm -rf off rtk's safe list, one named kubectl delete, bare lease, stash drop, prunes; dry-run flags pass. Own rows block credential-file reads (.env, keys, ~/.ssh) and echo or inline *_API_KEY/_SECRET/_TOKEN. Skips file rows in container exec. [Session-enforced by the PreToolUse hook under com.github.copilot/ in clients that read that namespace (documented for VS Code agent mode); a client that ignores it, as the Agent Plugins spec tells generic clients to, gets the advisory skill only. The hook needs git, a usable bash and a Python 3.11+ (python3, python or py, whichever actually runs). With no working Python it exits 2; without git or bash, fail-open clients allow silently and fail-closed clients refuse matched commands. If the guard itself crashes or times out, the hook asks for confirmation rather than allowing silently -- VS Code agent mode honours that ask and it overrides the client's own auto-approve.]

VersionCommitFirst seenUpdated
0.3.2latest422db8e6ba51
0.1.052ee3df0c643—