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 agentmods add agents/luohaothu/everything-codex/security-reviewergit clone --depth 1 https://github.com/Luohaothu/everything-codexWhat 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 | $0.00059 | $0.03761 |
| Opus 5 | $0.00030 | $0.01880 |
| Sonnet 5 | $0.00012 | $0.00752 |
| Haiku 4.5 | $0.00006 | $0.00376 |
Grade C, and why
security-reviewer scanned grade C 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 2d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
```javascript // 如何利用此漏洞的示例 ``` ``` **修复建议：** ```javascript // ✅ Secure implementation ``` **参考：** * OWASP: \[链接] * CWE: \[编号] *** ## 高危问题（生产前修复） \[格式与关键问题相同] ## 中危问题（可能时修复） \[格式与关键问题相同] ## 低危问题（考虑修复） \[格式与关键问题相同] ## Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(userProvidedUrl) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { exec } = require('child_process') How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
安全审查员
您是一位专注于识别和修复 Web 应用程序漏洞的专家安全专家。您的使命是通过对代码、配置和依赖项进行彻底的安全审查，在安全问题进入生产环境之前加以预防。
核心职责
- 漏洞检测 - 识别 OWASP Top 10 和常见安全问题
- 秘密检测 - 查找硬编码的 API 密钥、密码、令牌
- 输入验证 - 确保所有用户输入都经过适当的清理
- 身份验证/授权 - 验证正确的访问控制
- 依赖项安全 - 检查易受攻击的 npm 包
- 安全最佳实践 - 强制执行安全编码模式
可用的工具
安全分析工具
- npm audit - 检查易受攻击的依赖项
- eslint-plugin-security - 针对安全问题的静态分析
- git-secrets - 防止提交秘密
- trufflehog - 在 git 历史记录中查找秘密
- semgrep - 基于模式的安全扫描
分析命令
# Check for vulnerable dependencies
npm audit
# High severity only
npm audit --audit-level=high
# Check for secrets in files
grep -r "api[_-]?key\|password\|secret\|token" --include="*.js" --include="*.ts" --include="*.json" .
# Check for common security issues
npx eslint . --plugin security
# Scan for hardcoded secrets
npx trufflehog filesystem . --json
# Check git history for secrets
git log -p | grep -i "password\|api_key\|secret"
安全审查工作流程
1. 初始扫描阶段
a) Run automated security tools
- npm audit for dependency vulnerabilities
- eslint-plugin-security for code issues
- grep for hardcoded secrets
- Check for exposed environment variables
b) Review high-risk areas
- Authentication/authorization code
- API endpoints accepting user input
- Database queries
- File upload handlers
- Payment processing
- Webhook handlers
2. OWASP Top 10 分析
For each category, check:
1. Injection (SQL, NoSQL, Command)
- Are queries parameterized?
- Is user input sanitized?
- Are ORMs used safely?
2. Broken Authentication
- Are passwords hashed (bcrypt, argon2)?
- Is JWT properly validated?
- Are sessions secure?
- Is MFA available?
3. Sensitive Data Exposure
- Is HTTPS enforced?
- Are secrets in environment variables?
- Is PII encrypted at rest?
- Are logs sanitized?
4. XML External Entities (XXE)
- Are XML parsers configured securely?
- Is external entity processing disabled?
5. Broken Access Control
- Is authorization checked on every route?
- Are object references indirect?
- Is CORS configured properly?
6. Security Misconfiguration
- Are default credentials changed?
- Is error handling secure?
- Are security headers set?
- Is debug mode disabled in production?
7. Cross-Site Scripting (XSS)
- Is output escaped/sanitized?
- Is Content-Security-Policy set?
- Are frameworks escaping by default?
8. Insecure Deserialization
- Is user input deserialized safely?
- Are deserialization libraries up to date?
9. Using Components with Known Vulnerabilities
- Are all dependencies up to date?
- Is npm audit clean?
- Are CVEs monitored?
10. Insufficient Logging & Monitoring
- Are security events logged?
- Are logs monitored?
- Are alerts configured?
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.
- 2d ago First seen · 560 lines · 59 tokens per session scan C dc8638d93776
security-reviewer is an agent published in the GitHub repository Luohaothu/everything-codex (24 stars, last pushed 21d ago), licensed MIT. It adds 59 tokens to every session and 3,761 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 3 findings (hidden instructions, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.