{"version":"2.1.228","anchor":"model-backed-pre-flight-check-on-shell-commands-is-gone","canonical_anchor":"model-backed-pre-flight-check-on-shell-commands-is-gone","heading":"Model-backed pre-flight check on shell commands is gone","tier":"notice","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228\/e\/model-backed-pre-flight-check-on-shell-commands-is-gone","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228","markdown":"### Model-backed pre-flight check on shell commands is gone\n\nShell commands start faster because the safe prefix is now worked out locally.\n\n**What**\n\nClaude Code no longer sends a candidate shell command to a model to work out its safe prefix before running it. That means one fewer round-trip and one fewer thing that can stall or fail before a command starts. The prefix is now derived locally from the already-parsed command.\n\n**Details**\n\n- The removed results `command_injection_detected` and `dangerous_shell_prefix` no longer exist.\n- The 10-second message \"Pre-flight check is taking longer than expected\" can no longer appear.\n\n**Evidence**\n\n`dangerous_shell_prefix`\n\n- Area: Permissions\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}