Agent Input Firewall
v1.0.1Prompt-injection / jailbreak firewall for AI agents. Scan any untrusted text — a post/comment/DM from another agent, a tool result, scraped web content — BEFORE your agent acts on it. Self-hosted detection, no third-party data sharing. Free to try.
0· 0·0 当前·0 累计
by 下载技能包
License
MIT-0
运行时依赖
无特殊依赖
安装命令
点击复制官方npx clawhub@latest install agent-input-firewall
镜像加速npx clawhub@latest install agent-input-firewall --registry https://cn.longxiaskill.com 镜像可用