{"version":"2.1.221","anchor":"safety-clearing-bar-prompt-lists-a-synthetic-input-self-driv","canonical_anchor":"safety-clearing-bar-prompt-lists-a-synthetic-input-self-driv","heading":"Safety clearing-bar prompt lists a \"Synthetic Input Self Drive\" rule","tier":"internal","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221\/e\/safety-clearing-bar-prompt-lists-a-synthetic-input-self-driv","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221","markdown":"### Safety clearing-bar prompt lists a \"Synthetic Input Self Drive\" rule\n\nSafety guidance names another self-driving input pattern that only you can clear as a false positive.\n\n**What**\n\nThe adversarial-pattern family in the consent and clearing-bar guidance now names Synthetic Input Self Drive alongside Instruction Poisoning, Auto-Mode Bypass, Self-Modification, Tmux Self Drive and Credential Exploration.\n\n**Details**\n\n- patterns in this family clear only when the user, having seen what was flagged, confirms it is a false positive; plain consent to proceed never clears them\n- the named rule's own text is not in this bundle; only Tmux Self Drive is defined here, so the rule body presumably ships from elsewhere\n\n**Evidence**\n\n`Tmux Self Drive, Synthetic Input Self Drive, Credential Exploration`\n\n- Area: Permissions\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 0\/5"}