{"version":"2.0.30","anchor":"enhanced-sandbox-security-policy","canonical_anchor":"enhanced-sandbox-security-policy","heading":"Enhanced Sandbox Security Policy","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.0.30\/e\/enhanced-sandbox-security-policy","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.0.30","markdown":"### Enhanced Sandbox Security Policy\n\n**What:** A new configuration option `allowUnsandboxedCommands` that provides policy-level control over the `dangerouslyDisableSandbox` parameter.\n\n**How to use:**\n\n`\/\/ In your settings { \"sandbox\": { \"allowUnsandboxedCommands\": false \/\/ Enforce sandbox-only mode } }` **Details:**\n\n- **Default:** `true` (maintains backward compatibility)\n- **When set to `false`:** All commands run in sandbox mode regardless of the `dangerouslyDisableSandbox` parameter\n- **Enforcement:** The security check at `Q9A()` at line 249229 validates both the parameter AND the policy setting\n- **User communication:** Claude receives different system prompt instructions based on this setting (lines 208919-208942)\n- **Evidence**: Configuration schema at line 473000, getter function `XP8()` at line 208521"}