{"version":"2.1.225","anchor":"handoff-classifier-refusals-allow-the-output-with-an-unrevie","canonical_anchor":"handoff-classifier-refusals-allow-the-output-with-an-unrevie","heading":"Handoff classifier refusals allow the output with an unreviewed warning","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.225\/e\/handoff-classifier-refusals-allow-the-output-with-an-unrevie","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.225","markdown":"### Handoff classifier refusals allow the output with an unreviewed warning\n\nWhen a safety check on subagent handoff output is refused, the work passes through with a warning.\n\n**What**\n\nA sub-agent handoff whose safety classifier request is itself refused by the safeguard is no longer blocked; the output is passed through with a security warning attached.\n\n**Details**\n\n- The refusal is not treated as a verdict. The sub-agent output is allowed but prefixed with a long warning telling the model the work is unreviewed and untrusted.\n- Classifier outcome logging gained a \"refused\" bucket alongside the existing \"unavailable\" and \"blocked\".\n\n**Evidence**\n\n`Handoff classifier request refused by the safety safeguard, allowing sub-agent output with an unreviewed warning`\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 0\/5"}