agent-security
当你在设计 Agent 的安全防线、接入第三方工具/MCP/不可信输入、处理提示注入、越权操作、数据外泄时使用;当需要确定"谁能对什么数据做什么"的边界时使用。不适用于单一工具的参数校验实现(见 tool-design),聚焦分层防御架构与信任边界。
Source facts
- Repository
- GongLingRui/agent-dev-skills
- Last source activity
- August 27, 2026 at 01:47
- Detected SKILL.md language
- Chinese
- Stars
- 1
- Forks
- 0
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.