我搭建了一个运行时安全防护，阻止 AI 智能体做出愚蠢行为。
1 分•作者: thomaslwang•8 天前
大多数 AI 安全工具在问题发生后才检测到。我构建了 MoltGuard - 运行时防护栏，在执行之前阻止危险的工具调用。
安装：curl -s https://wry-manatee-359.convex.site/api/v1/download?slug=moltguard -o moltguard.zip
目前已有超过 16000 次下载，保护 AI 代理免受诸如删除生产数据库或泄露凭据等愚蠢行为的侵害。
查看原文
Most AI security tools detect problems AFTER they happen. I built MoltGuard - runtime guardrails that block dangerous tool calls BEFORE execution.<p>Install: curl -s https://wry-manatee-359.convex.site/api/v1/download?slug=moltguard -o moltguard.zip<p>Currently at 16K+ downloads protecting AI agents from doing dumb things like deleting production databases or leaking credentials.