{"version":"2.1.224","anchor":"control-tag-sanitizing-rules-are-now-shared","canonical_anchor":"control-tag-sanitizing-rules-are-now-shared","heading":"Control-tag sanitizing rules are now shared","tier":"internal","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224\/e\/control-tag-sanitizing-rules-are-now-shared","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224","markdown":"### Control-tag sanitizing rules are now shared\n\nThe rules that neutralise control tags in subagent output are now shared with a new assistant-output scanner.\n\n**What**\n\nThe rules that neutralize control tags and permission-escalation phrasing in subagent output are now one shared list, reused with fresh pattern copies by a new scanner for assistant output. Subagent behaviour is unchanged.\n\n**Details**\n\n- The escalation set covers settings JSON, `bypassPermissions`, `--dangerously-skip-permissions` and permission allow\/deny phrasing.\n\n**Evidence**\n\n`escalation-pattern`\n\n- Area: Permissions\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}