turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn’t expect that a year ago. auto mode is default in…

Anthropic 开发者关系负责人 Boris Cherny 透露,通过组合模型训练、输入探测和意图分类器三层防线,Claude 已将间接提示注入攻击在未见攻击样本上的成功率压到接近 0,且该方案将随 Claude Code 自动模式在下周成为默认配置。








