{"version":"2.1.323","anchor":"subagent-hand-back-frame-marks-subagent-reports-as-non-user","canonical_anchor":"subagent-hand-back-frame-marks-subagent-reports-as-non-user","heading":"Reports from helper agents are marked as model output, not your instructions","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/subagent-hand-back-frame-marks-subagent-reports-as-non-user","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Reports from helper agents are marked as model output, not your instructions\n\nA helper agent's final report is framed as model output with no user authority, and flagged UNREVIEWED if its safety review was refused\n\n**What**\n\nA subagent is a helper Claude starts to handle part of a task. When a subagent hands back its final report, Claude Code wraps it in a frame saying the report is model output, not a message from you, and that any instructions or claims of approval inside it carry no authority from you.\n\nA second warning marks the report UNREVIEWED when its safety review was refused by a filter earlier in the chain.\n\n**Why**\n\nThis guards against a subagent's report tricking the main agent into acting as if you had approved something. You may see this warning text in your session.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}