{"version":"2.1.311","anchor":"bash-permission-analysis-touseron-and-a-do-keyword-loop-che","canonical_anchor":"bash-permission-analysis-touseron-and-a-do-keyword-loop-che","heading":"Shell command safety check looks harder at loop keywords","tier":"notice","area":"Bash Safety","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.311\/e\/bash-permission-analysis-touseron-and-a-do-keyword-loop-che","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.311","markdown":"### Shell command safety check looks harder at loop keywords\n\nWhen checking a shell command, Claude Code now re-reads any word containing do plus whitespace, up to a set limit\n\n**Unclear.** What a reader will notice from this, such as more permission prompts, is not stated.\n\n**What**\n\nBefore running a shell command, Claude Code checks it to decide whether it is safe to run without asking you. That check now takes a second look at any word that contains `do` followed by whitespace, as found in shell loops. It parses that word again and stops after a set amount of work. The check's result also gains a new field.\n\n**Why**\n\nIt makes the shell safety check stricter.\n\n- Area: Bash Safety\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}