Claude Code 默认启用自动模式，Anthropic 宣称安全评估结果优异
原标题：Auto mode is now the default in Claude Code for Pro, Max, and Team plans
AI 摘要
Anthropic 宣布自 2026 年 8 月 14 日起，Claude Code 的 Pro、Max 和 Team 计划将默认启用自动模式。Anthropic 声称其自动模式已大幅缓解提示注入和数据泄露风险，并发布了相关评估，包括对 1053 名付费测试者的实验，结果显示自动模式可阻止 89% 的危险操作，而人类仅拒绝 13.6%。然而，作者 Simon Willison 对此持保留态度，认为仍需独立验证，并指出自动模式可能无法防御某些恶意第三方包攻击。
正文节选
8th August 2026 - Link Blog Auto mode is now the default in Claude Code for Pro, Max, and Team plans (via) Anthropic are really confident in Claude Code's auto mode, to the point that they are making it the default setting for new sessions in most Claude Code plans starting on August 14th. This was one of the topics discussed in our Fireside Chat with Cat Wu and Thariq Shihipar at the AI Engineer World’s Fair last month. I asked them how they run Claude Code safely within Anthropic (given the th