What is metago-security-audit?

A security review skill based on the OWASP Top 10, a commonly used list of major web-application security risks. It checks code, dependencies, configuration, authentication, and data handling.

Use it for security audits, vulnerability scans, penetration-test support, dependency checks, CVE review, risk ratings, and repair recommendations.

It helps find vulnerabilities and exposed secrets before software is released or sensitive changes are merged.

metago-security-audit — Skill for Claude Code and Codex by metago-ai

Install

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.

Any agent

npx skills add metago-ai/metagolifeform --skill metago-security-audit

Clone the repo

git clone --depth 1 https://github.com/metago-ai/metagolifeform

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-security-audit/github.svg)](https://agentmods.dev/skills/metago-ai/metagolifeform/metago-security-audit)

Your own site

<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-security-audit"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-security-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-security-audit"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,750 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00075	$0.01750
Opus 5	$0.00037	$0.00875
Sonnet 5	$0.00015	$0.00350
Haiku 4.5	$0.00007	$0.00175

Measured 12d ago against content hash 41e36cba58c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

metago-security-audit scanned grade A with 0 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 12d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/dev-kit/skills/metago-security-audit/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

安全审计（metago-security-audit）

描述

基于 OWASP Top 10 进行多维度安全审计，检测注入漏洞、认证授权缺陷、敏感信息泄露、依赖漏洞。输出含 CVE 引用、漏洞等级、修复方案的结构化报告。遵循 A36 法律优先于效率原则。

触发条件

用户请求安全审计、漏洞扫描、渗透测试时激活
代码合并前安全审查
依赖更新时安全评估
与 metago-compliance 协同：合规检查时联动安全审计
涉及用户数据、支付、权限的功能强制触发

核心流程

1. OWASP Top 10 检查

A01 - 失效的访问控制

路径遍历漏洞（../、绝对路径）
越权访问（水平/垂直越权）
未授权 API 端点
缺失权限校验

A02 - 加密失败

明文传输（HTTP、未加密 WebSocket）
弱加密算法（MD5、SHA1、DES）
硬编码密钥/证书
敏感数据明文存储

A03 - 注入

SQL 注入（拼接查询、未参数化）
命令注入（shell 拼接、eval）
XSS（反射型、存储型、DOM 型）
LDAP/XPath/NoSQL 注入

A04 - 不安全设计

缺失威胁建模
不安全的业务流程（可重放、可绕过）
缺失速率限制（暴力破解、DoS）
敏感操作无二次确认

A05 - 安全配置错误

默认凭证未修改
错误信息泄露堆栈/路径
不安全的 HTTP 头（缺失 CSP、HSTS）
不必要的功能启用（DEBUG、TRACE）

A06 - 易受攻击的组件

已知 CVE 的依赖
过时依赖（超过 N 个版本）
未经审计的依赖（无签名、无 SBOM）
供应链攻击风险

A07 - 认证失败

弱密码策略
会话管理缺陷（固定会话、不过期）
缺失多因素认证（高权限场景）
凭证填充防护缺失

A08 - 数据完整性失败

反序列化漏洞
未签名的更新/插件
CI/CD 管道安全
代码注入（include/require 用户输入）

A09 - 日志与监控失败

安全事件未记录
日志包含敏感信息
缺失告警机制
日志可篡改

A10 - 服务端请求伪造（SSRF）

用户输入直接用于 URL 请求
内网访问未限制
协议白名单缺失
DNS 重绑定

2. 依赖漏洞扫描

检查 package.json / pom.xml / requirements.txt 依赖版本
比对 CVE 数据库
评估漏洞可利用性（CVSS 评分）
生成升级建议

3. 敏感信息检测

硬编码密钥（API Key、Token、Password）
日志中的敏感数据
配置文件中的明文凭证
Git 历史中的敏感信息

漏洞等级标准

等级	CVSS	含义	处理时效
🔴 Critical	9.0-10.0	立即修复（RCE、数据泄露）	24 小时内
🟠 High	7.0-8.9	尽快修复（注入、越权）	7 天内
🟡 Medium	4.0-6.9	计划修复（信息泄露）	30 天内
🔵 Low	0.1-3.9	评估修复（配置优化）	下个版本

输出格式

【安全审计报告】

## 1. 审计概览
审计范围：[文件/模块/项目]
审计时间：YYYY-MM-DD
总体安全评级：A/B/C/D/F
漏洞统计：Critical=N, High=N, Medium=N, Low=N

## 2. 漏洞详情

### 🔴 Critical
[V-001] [漏洞名称]
  类型：OWASP A0X - [类别]
  位置：file.ext:LXX
  描述：...
  影响：...
  CVE：CVE-2024-XXXX（如适用）
  CVSS：X.X
  修复方案：
    1. ...
    2. ...
  参考标准：...

### 🟠 High
[V-002] ...

### 🟡 Medium
[V-003] ...

### 🔵 Low
[V-004] ...

## 3. 依赖漏洞
| 依赖 | 当前版本 | 漏洞版本 | CVE | CVSS | 建议版本 |
|------|----------|----------|-----|------|----------|
| ... | ... | ... | ... | ... | ... |

## 4. 敏感信息检测
| # | 类型 | 位置 | 风险 | 处理建议 |
|---|------|------|------|----------|
| 1 | 硬编码 API Key | file.ext:LXX | 高 | 移至环境变量 |

## 5. 安全配置检查
| 检查项 | 状态 | 建议 |
|--------|------|------|
| HTTPS 强制 | ✅/❌ | ... |
| CSP 头 | ✅/❌ | ... |
| HSTS | ✅/❌ | ... |
| 速率限制 | ✅/❌ | ... |

## 6. 审计结论
安全状态：✅ 通过 / ❌ 需修复后重新审计
合规状态：符合 / 不符合 [标准名]
优先修复项：V-001, V-002

Read the full file on GitHub · 179 lines

Changes

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.

12d ago First seen · 179 lines · 75 tokens per session scan A 41e36cba58c1

Subscribe to this mod's changes

metago-security-audit is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 1,750 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security agentive-os ai-agent ai-evolution ai-governance ai-lifeform anti-hallucination 公众号

card-xiaohongshu

Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.

nexu-io/open-design · 25 tokens

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

semantica-agi/semantica · 59 tokens

metago-security-audit