{"version":"2.1.318","anchor":"control-tag-forgery-gate-with-telemetry","canonical_anchor":"control-tag-forgery-gate-with-telemetry","heading":"A faster first check before cleaning up fake control tags","tier":"internal","area":"Prompt Safety","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/control-tag-forgery-gate-with-telemetry","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### A faster first check before cleaning up fake control tags\n\nClaude Code can run a quick first check before neutralising fake control tags in content, controlled by a remote setting\n\n**What**\n\nClaude Code removes text that pretends to be its own internal control tags, so outside content cannot pass itself off as instructions. That clean-up can now be preceded by a quicker first check, switched by a remote setting. Claude Code also counts how often the check matches, misses or fails.\n\nWhen the server sends nothing, the setting falls back to not treating the check as safe to use.\n\n**Why**\n\nThis is about making the defence against prompt injection, where text tries to trick Claude into following it, faster without weakening it.\n\n- Area: Prompt Safety\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}