agentleFS
cheukswisscheukswiss/etdxm/.claude/skills/redline-reference/SKILL.md

redline-reference

Skill2 starsChanged 6 months agoMITView on GitHub

刑部红线清单 R01-R10(刑部常驻加载),安全合规审查的不可违反规则

The file

Files
SKILL.md

Skill: 刑部红线清单

适用 Agent:刑部(常驻)、工部/兵部等(被驳回时查阅) 加载时机:刑部审查时;其他 Agent 收到红线驳回时

红线规则(R01-R10)

编号红线规则说明
R01注入防护禁止拼接 SQL、未转义用户输入(SQL 注入、XSS、命令注入)
R02认证鉴权所有接口必须有权限校验,禁止硬编码凭据
R03敏感数据密码必须哈希存储,密钥禁止提交至代码仓库
R04依赖安全禁止引入已知高危漏洞的依赖,定期更新
R05日志合规日志中禁止记录敏感信息(密码、Token、身份证号等)
R06输入校验所有外部输入必须校验与消毒,拒绝信任外部数据
R07错误处理禁止向用户暴露内部错误栈,生产环境关闭调试模式
R08HTTPS生产环境所有通信必须加密传输
R09越权代办Agent 不得执行超出自身职责范围的任务(如太子直接开发、六部自行规划)。豁免:降级与上级亲办场景除外,须事后补审
R10跨级通信违反通信权限矩阵的通信行为(如六部绕过尚书省直接联系三省/皇上,P0 紧急除外)

违反后果

刑部直接打回产出物至对应产出部门,标记 rejected,必须修复后重新提交。红线不可商量,灰色地带从严处理。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.