Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.47 Home All releases ←olderv2.1.45 v2.1.48newer→
Claude Code v2.1.47

Enhanced Dangerous Command Warnings

What

Bash commands that may have destructive effects now show detailed warning notes explaining the potential impact.

Details
  • New warning notes for potentially dangerous commands:
  • Note: may delete Kubernetes resources
  • Note: may delete all rows from a database table
  • Note: may destroy Terraform infrastructure
  • Note: may discard all working tree changes
  • Note: may discard uncommitted changes
  • Note: may drop or truncate database objects
  • Note: may force-delete a branch
  • Note: may force-remove files
  • Note: may overwrite remote history
  • Note: may permanently delete untracked files
  • Note: may permanently remove stashed changes
  • Note: may recursively force-remove files
  • Note: may rewrite the last commit
  • Note: may skip safety hooks
  • Blocked commands show "Permission for this action was denied by the dangerous action safety classifier"
Evidence

Warning note strings (search for "Note: may delete", "dangerous action safety classifier")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.47 →