Secure Vibe
Description
Open-source security skill for AI agents (opencode / Codex / Claude Code). Detects 97 secret/injection/deserialization/XSS/SSRF/XXE/IaC rules across Python, C/C++, PHP, HTML, JS/Node, Go, Java, Shell, Docker, K8s, Terraform & GitHub Actions — fully offline, no API key, JSONL audit logs.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Secure-Vibe — 生成时安全的代码生成 Skill
[](LICENSE)   
在 vibe-coding(AI 自由生成代码)场景中,**在代码生成过程中就引导模型写出安全代码**—— 不是"先生成后检查",而是:安全上下文注入 → 生成 → 毫秒级校验 → 自动修复循环。
两种使用模式
跨 Agent 安装(opencode / Codex / Claude Code)
本 Skill 使用各主流 Agent 通用的 SKILL.md 格式(frontmatter: `name` + `description`), 校验器 `cli.py` 相对自身定位规则/模板、**不依赖工作目录**,任何能执行 shell 的 Agent 均可调用:
| Agent | 默认技能目录 | 安装命令 |
|---|---|---|
| opencode | ~/.config/opencode/skill/secure-vibe |
./install.sh 或 powershell -File install.ps1 |
| Codex | ~/.codex/skills/secure-vibe |
./install.sh codex 或 powershell -File install.ps1 -Agent codex |
| Claude Code | ~/.claude/skills/secure-vibe |
./install.sh claude 或 powershell -File install.ps1 -Agent claude |
| 其他/自定义 | 任意 | ./install.sh /path/to/skills/secure-vibe 或 -Target "C:\..." |
- 运行依赖:任意 Python 3.7+(Linux/macOS 用
python3)+pyyaml(pip install pyyaml,见requirements.txt)。安装脚本自动探测带 pyyaml 的解释器并跑selftest自检。 context/validate/log/selftest均为本地毫秒级执行,零网络、零 API Key。
模式 A:安装进 Agent(推荐,Skill 的主形态)
把本 Skill 安装到 Agent(opencode / Codex / Claude Code / 任意支持技能目录的框架), 生成由 **Agent 自身的 LLM** 完成(session 模式),本 Skill 提供 上下文构建 / 毫秒级校验 / 修复指令 / 日志 四个确定性工具,**零 API 依赖、零密钥**。
# Windows(默认安装到 opencode 技能目录)
powershell -File install.ps1
# Codex / Claude Code
powershell -File install.ps1 -Agent codex
powershell -File install.ps1 -Agent claude
# Linux / macOS
./install.sh # 默认 opencode
./install.sh codex # Codex
./install.sh claude # Claude Code
安装脚本自动复制技能文件并运行自检(`cli.py selftest`)。重启 Agent 后, Agent 在写代码前会执行:
① cli.py context --task "..." # 加载安全规则(写代码之前)
② (Agent 自身 LLM 生成代码)
③ cli.py validate --file f.py # 毫秒级校验(exit 1 =
Related Skills
Fastapi Review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu
Security Defense in Depth
Implement multi-layered testing and security best practices.
Security SecLists Official Repository
[OWASP Testing Guide](https://owasp.org/www-project-web-security-testing-guide/)
Security Threat Hunting with Sigma Rules
Use Sigma detection rules to hunt for threats and analyze security events
Security Maintenance Walkthrough - 2026-03-29
- Re-triaged the full 2026-03-15 security finding set against current `main` and wrote a fresh current-head re
Security Google Workspace Model Armor
Filter user-generated content for safety
Security Related Agents
Django Reviewer
Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfi
Token Auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,