{"version":"2.1.221","anchor":"security-review-prompt-handles-subagent-hand-back-messages","canonical_anchor":"security-review-prompt-handles-subagent-hand-back-messages","heading":"Security review prompt handles subagent hand-back messages","tier":"notice","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221\/e\/security-review-prompt-handles-subagent-hand-back-messages","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.221","markdown":"### Security review prompt handles subagent hand-back messages\n\nSecurity review no longer misses issues when a subagent's hand-back message is the last thing in the transcript.\n\n**What**\n\nThe reviewing model is told how to judge a subagent's final hand-back message when it is the last thing in the transcript.\n\n**Details**\n\n- new BLOCK-rule bullet: when the final entry to evaluate is a handoff review carried in tags, that text is itself the action to judge\n- prevents the model concluding there was no action just because no tool call trails it\n\n**Evidence**\n\n`- SUBAGENT HAND-BACK: When the final entry to evaluate is a handoff review`\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 0\/5"}