Skip to main content
在 Manus 中运行任何 Skill
一键导入

tool-security

星标0
分支0
更新时间2026年4月2日 15:10

Design secure tool systems for AI agents using the dual-defense pattern (prompt guidance + code enforcement). Use when (1) designing tool prompts with preference chains and safety constraints, (2) implementing code-layer security checks for agent tool calls, (3) building tool permission and sandbox systems, (4) auditing existing tool security architectures. Triggers on phrases like tool security, agent tool design, preference chain, sandbox, tool permission, dual defense.

安装

用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。

SKILL.md
readonly