Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skillmds/skillmd --skill 04-securitygit clone --depth 1 https://github.com/skillmds/skillmdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skillmds/skillmd/04-security)<a href="https://agentmods.dev/skills/skillmds/skillmd/04-security"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/04-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skillmds/skillmd/04-security"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/04-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.05189 |
| Opus 5.5 | $0.00014 | $0.02076 |
| Sonnet 5 | $0.00007 | $0.01038 |
| Haiku 4.5 | $0.00004 | $0.00519 |
Grade A, and why
04-security scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost/health How it starts
The opening of the file, as written. The whole thing — 809 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dify 安全和部署 SKILL
概述
本 SKILL 提供 Dify 平台的安全实践和部署运维完整指南，帮助开发者和运维人员构建安全、稳定、高性能的生产环境。
触发场景
使用本 SKILL 当你需要:
- 🚀 部署 Dify 到生产环境 (Docker/Kubernetes)
- 🔒 配置安全防护机制 (SSRF、沙箱、加密)
- 🔧 解决部署问题 (容器启动失败、网络配置、性能瓶颈)
- 📊 优化生产环境 (监控告警、高可用、故障恢复)
- ✅ 进行安全审计 和配置验证
核心能力
- 安全防护: SSRF 防护、代码沙箱、数据加密、权限管理
- Docker 部署: 快速部署、生产配置、网络架构、资源优化
- Kubernetes 部署: 高可用架构、自动扩展、Helm 部署
- 监控告警: OpenTelemetry、Sentry、日志聚合、性能监控
- 故障恢复: 问题诊断、恢复流程、备份策略
快速开始
最小部署配置
# 1. 克隆仓库
git clone https://github.com/langgenius/dify.git
cd dify/docker
# 2. 复制环境变量
cp .env.example .env
# 3. 修改关键安全配置
# 编辑 .env 文件:
SECRET_KEY=$(openssl rand -base64 42)
DB_PASSWORD=your-strong-password
REDIS_PASSWORD=your-redis-password
SANDBOX_API_KEY=$(openssl rand -base64 32)
# 4. 启动服务
docker compose up -d
# 5. 验证部署
docker compose ps
curl http://localhost/health
安全检查清单
部署前检查
- SECRET_KEY 已更改为强密钥 (使用
openssl rand -base64 42) - 数据库密码 已修改默认值
- Redis 密码 已设置
- SSRF Proxy 已配置并阻止内网访问
- Sandbox 沙箱 已启用网络代理
- HTTPS/TLS 证书已配置 (生产环境)
- API Key 管理 机制已启用
- 文件上传限制 已设置 (UPLOAD_FILE_SIZE_LIMIT)
- 敏感环境变量 已加密存储
运行时检查
- 容器权限 以非 root 用户运行
- 网络隔离 ssrf_proxy_network 正常工作
- 健康检查 所有服务健康状态正常
- 日志记录 已启用并正常输出
- 监控告警 已配置 (OpenTelemetry/Sentry)
- 备份策略 已实施 (数据库、文件存储)
- 资源限制 CPU/内存限制已配置
- SSL 证书 有效期检查和自动续期
目录结构
04-security/
├── SKILL.md # 本文件 - 安全和部署总览
├── security/ # 安全实践
│ ├── ssrf-protection.md # SSRF 防护配置
│ ├── sandbox.md # 代码沙箱隔离
│ ├── encryption.md # 数据加密和 TLS
│ └── auth.md # 认证和权限管理
├── deployment/ # 部署指南
│ ├── docker-compose.md # Docker Compose 部署
│ ├── kubernetes.md # Kubernetes 部署
│ ├── serverless.md # Serverless 部署
│ └── high-availability.md # 高可用架构
├── operations/ # 运维实践
│ ├── monitoring.md # 监控和告警
│ ├── logging.md # 日志管理
│ ├── backup.md # 备份和恢复
│ └── troubleshooting.md # 故障排查
└── best-practices.md # 最佳实践总结
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 809 lines · 36 tokens per session scan A 50a746e5fc37
04-security is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 5,189 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
04-security
A security and deployment guide for the Dify platform, an application for building AI-powered services.
deployment
Kubernetes Deployment 管理.
nestjs-deployment
Containerize NestJS apps with multi-stage Docker builds, tune Node.js memory, and implement graceful shutdown hooks. Use when writing Dockerfiles, configuring K8s deployments, or adding shutdown hooks for NestJS.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
agentbox-info
Spin up isolated sandboxes ("boxes") for coding agents, run them in parallel, queue background runs with -i, and push commits safely through the host relay. Use when the user wants to run Claude Code / Codex / OpenCode in a sandbox, start more boxes, attach to a running box, or otherwise operate the agentbox CLI on…
k8s-agent-sandbox-mcp
An MCP server skill for managing Kubernetes sandboxes. Enables creating, executing commands, managing files, and terminating instances via the official kubernetes-sigs/agent-sandbox MCP server.