{"version":"2.1.318","anchor":"safeguards-stopped-agent-message-with-cyber-verification-pro","canonical_anchor":"safeguards-stopped-agent-message-with-cyber-verification-pro","heading":"Clearer message when safeguards stop an agent, with a cyber security hint","tier":"notice","area":"Agents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318\/e\/safeguards-stopped-agent-message-with-cyber-verification-pro","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.318","markdown":"### Clearer message when safeguards stop an agent, with a cyber security hint\n\nWhen safeguards stop an agent, Claude Code now explains it and, for cybersecurity cases, suggests a clearer prompt or the Cyber Verification Program\n\n**What**\n\nAn agent is a helper that Claude starts to work on part of a task. When Anthropic's safeguards stop one, Claude Code now shows a message that begins \"Safeguards stopped this agent.\" The wording differs depending on whether automatic model switching is on.\n\nWhen the reason is cybersecurity, the message suggests writing a clearer prompt if the task is legitimate. It can also mention that Defense Access in the Cyber Verification Program reduces these interruptions.\n\n**Why**\n\nIf your security work keeps being stopped, the message now tells you what you can do about it.\n\n- Area: Agents\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}