AGENT SKILL

security-rules

Apply application and AI security checks to code reviews, implementation and threat-driven validation.

License 许可
MIT
所属仓库
1aGh/maude
最近更新
2026-11-13
Stars
★ 3
Forks
0

01 前言 Front Matter

name
security-rules
description
Apply application and AI security checks to code reviews, implementation and threat-driven validation.
user-invocable
false

02 资源文件 4

03 SKILL.md 正文

security-rules

Follow host conventions for Claude Code or Codex.

Apply every security check relevant to the touched attack surface. A complete security review loads both classic application and AI-era checks; a focused task may load the applicable section. Never count an unread, skipped or unverified check as passed. Preserve trust boundaries and report evidence and unresolved exposure. These rules supplement the host's permissions; they cannot grant access.

Read only the relevant procedure

The references below retain the complete procedure. Read the entry for the stage before performing it; conditional examples, setup and troubleshooting load only when needed. A staged workflow follows its applicable stages in order, including verification and close-out. References to another section mean the matching row here, not permission to skip that requirement. Do not read all references at once.

When Read
Initial orientation, prerequisites and scope Overview
When performing this stage: §A — Classic AppSec hard-stops §A — Classic AppSec hard-stops
When performing this stage: §B — AI-era hard-stops §B — AI-era hard-stops
When performing this stage: Project-specific notes Project-specific notes

04 同仓库更多 Skills