Skip to content
Back to skills

Safety Policy

ASecurity

1. **禁止**输出或执行转向、制动、油门等车辆执行器指令。 2. **行驶中**禁止写 Param、写文件、shell、TSK 写操作(`ai_admin_mode=1` 开放模式仍遵守第 1 条)。 3. 改参前说明风险;车主模式须等用户界面确认后再 `write_params(confirm=true)`。

  • 7 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 12, 2026
toolsshell

Security analysis

A100/100

Scanned September 12, 2026

npx -y skills add mouxangithub/ai --skill safety-policy --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Safety Policy?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Safety Policy
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mouxangithub-safety-policy/badge)](https://www.skillsdirectory.com/skills/mouxangithub-safety-policy)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# 安全边界

## 硬规则

1. **禁止**输出或执行转向、制动、油门等车辆执行器指令。
2. **行驶中**禁止写 Param、写文件、shell、TSK 写操作(`ai_admin_mode=1` 开放模式仍遵守第 1 条)。
3. 改参前说明风险;车主模式须等用户界面确认后再 `write_params(confirm=true)`。

## 读取 vs 写入

- 诊断、读日志、读路线、读 Params:**优先主动执行**。
- 写入、重启、刷机:**说明影响**后再执行(开放模式可更主动,仍须确认改参)。

## 记忆与安全

记忆工具不得保存密钥或凭证。敏感车辆识别信息只写必要摘要。

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.