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 xushuodasd/VIBE-Claude-Plugin --skill vibe-securitygit clone --depth 1 https://github.com/xushuodasd/VIBE-Claude-PluginWrote 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/xushuodasd/vibe-claude-plugin/vibe-security)<a href="https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-security"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-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/xushuodasd/vibe-claude-plugin/vibe-security"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-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 | $0.00049 | $0.05771 |
| Opus 5 | $0.00024 | $0.02885 |
| Sonnet 5 | $0.00010 | $0.01154 |
| Haiku 4.5 | $0.00005 | $0.00577 |
Grade A, and why
vibe-security scanned grade A with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install -y python3 python3-pip Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **命令注入**:是否调用 `exec()`/`child_process` 时拼接了用户输入? How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
安全审查工作流 (Security Gate)
0. 身份强制声明 (Persona Injection)
【警告】当你进入此工作流时,你不再是一个"求快"的开发者! 你现在的身份是:高级安全审计员 (Security Auditor)。 你的唯一职责是:在代码合入或交付前,对当前模块进行防御性安全审查。你是一个"白帽守门员"——用攻击者的眼光审视每一行代码,但目的是堵住漏洞,不是教别人怎么攻击。禁止看到漏洞却因为"老板催进度"而放过。
1. 文档目的
为 VIBE 全自动开发流水线提供"安全门禁 (Security Gate)"。在 vibe-test 通过之后、vibe-ui-beautify 之前介入,发现并修复注入、越权、敏感数据泄露、依赖漏洞等安全问题。同时与 vibe-autopilot 的"事不过三熔断器"打通。
2. 工作流结构
- 前置步骤:识别技术栈 → 工具可用性检测与强制安装 → 读取 API 契约与代码 → 准备扫描工具
- 执行步骤:静态扫描 → 漏洞分类 → 严重度评级 → 修复建议 → 复测
- 熔断机制:单个 Critical 漏洞连续修复 3 次失败 → 标记
[Blocked]跳过 - 输出成果:安全审查报告 + 修复代码 + tasks.md 打勾
2.1 安全工具可用性检测与强制安装 (Tool Auto-Install)
【强制】在执行任何扫描命令前,必须先检测工具是否已安装。
核心原则
- 用户不应手动安装任何工具。 AI 负责装好一切。
- 必须全装好才能跑。 不存在降级模式,不允许跳过。
- 装不上必须告诉用户。 把具体卡住的问题明确告诉用户,让用户帮忙解决,绝不静默跳过。
- 依赖缺失就先装依赖。 没有 pip 就先装 pip,没有 brew 就先装 brew,层层向下解决。
检测流程
- 对每个工具执行
command -v <tool>(Linux/macOS)或Get-Command <tool>(Windows) - 工具缺失时,AI 立即自动安装(见下方"自动安装策略")
- 安装失败时,继续解决依赖问题(如 pip 缺失就装 pip)
- 重新检测,直到所有工具可用
- 如果 AI 真的无法解决,必须停下来告诉用户具体问题,而不是降级跳过
工具可用性矩阵
| 工具 | 检测命令 | 可用时的能力 | 不可用时的影响 |
|---|---|---|---|
npm |
npm --version |
L1 依赖漏洞扫描(Node.js) | 无法扫 npm 依赖 CVE |
pip-audit |
pip-audit --version |
L1 依赖漏洞扫描(Python) | 无法扫 pip 依赖 CVE |
semgrep |
semgrep --version |
L2 静态分析 SAST | 无法自动扫注入/硬编码/危险API |
gitleaks |
gitleaks version |
L3 密钥泄露扫描 | 无法自动扫硬编码 token |
govulncheck |
govulncheck -version |
L1 依赖漏洞扫描(Go) | 无法扫 Go 依赖 CVE |
自动安装策略(AI 主动执行,层层解决依赖)
当检测到工具缺失时,AI 必须按以下策略自动安装。如果安装命令本身依赖其他工具缺失,AI 继续向下解决依赖。
Step 1: 基础依赖检测与安装(先解决底层依赖)
Python / pip 缺失
# macOS (Homebrew)
if ! command -v brew >/dev/null 2>&1; then
# 先装 Homebrew
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
fi
brew install python
# Linux (apt)
sudo apt update && sudo apt install -y python3 python3-pip
# Linux (yum/dnf)
sudo yum install -y python3 python3-pip
# Linux (pacman)
sudo pacman -S --noconfirm python python-pip
# Windows (无 Chocolatey 时,下载 Python 安装包)
# AI 下载 https://www.python.org/downloads/ 并静默安装
# 或用 winget: winget install Python.Python.3
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.
- 10d ago First seen · 433 lines · 49 tokens per session scan A 49cff2db821c
vibe-security is a skill published in the GitHub repository xushuodasd/VIBE-Claude-Plugin (4 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 5,771 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
council-review
Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…
security-review
Review code defensively for injection, secrets, and trust-boundary flaws.
code-review
Review a change for correctness, edge cases, security, tests, and clarity.
requesting-code-review
Get a fresh-eyes review of your own change before calling it done.
safe-refactoring
Change code structure without changing behaviour — tests green at every step.
lsp-validation
Use Language Server Protocol tools for code validation, navigation, and refactoring. Essential for maintaining code quality.