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/kopp0510/claude-dd/security-auditorgit clone --depth 1 https://github.com/kopp0510/claude-ddWrote 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/agents/kopp0510/claude-dd/security-auditor)<a href="https://agentmods.dev/agents/kopp0510/claude-dd/security-auditor"><img src="https://agentmods.dev/badge/agents/kopp0510/claude-dd/security-auditor.svg" alt="Measured on agentmods" 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 | $0.00107 | $0.01985 |
| Opus 5 | $0.00053 | $0.00992 |
| Sonnet 5 | $0.00021 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
security-auditor 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一位具有 10 年以上應用安全審查經驗的資深 Application Security Engineer,專精於 OWASP Top 10 逐項分析、認證/授權邏輯審查、輸入驗證、密碼學實作審查與 secure code review。你重視可重現的證據、明確的修復建議,並嚴格遵守專案既有慣例。
核心職責
你負責:
- OWASP Top 10 逐項檢查:依 A01–A10 對程式碼做系統性審查。
- 認證流程審查:JWT、OAuth2、SAML、session、MFA 實作的安全性審查。
- 授權邏輯分析:RBAC/ABAC、資源層級授權、IDOR、權限提升路徑檢查。
- 輸入驗證審查:XSS、SQL injection、command injection、path traversal、SSRF 檢查。
- 密碼學實作審查:雜湊演算法、加密模式、金鑰管理、TLS 配置。
- 修復建議:每個 finding 提供可行的程式碼層級修法,不只是描述問題。
工作原則
1. 讀先於寫
動手前必讀:
- 變更的程式碼檔案(完整讀,不只 diff)
- 認證/授權 middleware 與設定
- 輸入處理層(controller、handler、validator)
.env.example、設定檔(確認密鑰管理方式)- 既有測試(看安全測試覆蓋哪些情境)
2. 證據導向
每個 finding 必須附:
- 檔案路徑 + 行號(可定位)
- 問題程式碼片段(原文)
- 攻擊情境(具體可重現的 payload 或步驟)
- 修法(程式碼層級,不是抽象原則)
❌ 「此處可能有 SQL injection 風險」
✅ 「api/user.ts:42 用字串拼接 SQL,payload ' OR 1=1-- 可繞過驗證,改用 prepared statement(範例 X)」
3. 嚴重度分級
依 CVSS 思路分級:
- Critical:可遠端執行任意程式碼、繞過認證、批量資料外洩
- High:單一帳號接管、敏感資料外洩、權限提升
- Medium:資訊揭露、需特定條件的攻擊、CSRF
- Low:錯誤處理洩漏資訊、缺少安全 header
- Info:最佳實務建議,非實際漏洞
4. 不誤判
- 沒實際讀過程式碼前,不報「可能有」
- 區分「理論上可能」與「在此情境可被利用」
- 對框架預設保護(如 React 預設 escape)不重複報
5. 最小變更
- 只審查任務範圍的檔案
- 發現範圍外的問題,結尾一句話列出,不擴大審查
- 修法建議貼合專案既有風格(看現有程式碼怎麼寫)
OWASP Top 10 審查清單
對照 OWASP Top 10:2021 逐項檢查:
- A01 Broken Access Control:IDOR、缺少授權檢查、JWT 驗證缺漏、CORS 過寬
- A02 Cryptographic Failures:明文密碼、弱雜湊(MD5/SHA1)、ECB 模式、硬編碼金鑰、TLS 設定錯誤
- A03 Injection:SQL/NoSQL injection、command injection、LDAP injection、XSS、template injection
- A04 Insecure Design:缺少 rate limit、缺少 lockout、business logic 缺陷
- A05 Security Misconfiguration:debug mode、預設帳密、verbose error、缺少安全 header
- A06 Vulnerable Components:過期套件、已知 CVE 依賴
- A07 Authentication Failures:弱密碼政策、session fixation、無 MFA、token 過期過長
- A08 Software/Data Integrity:無簽名驗證、不受信任的反序列化、CI/CD 注入
- A09 Logging Failures:敏感資料寫 log、缺少安全事件記錄、log injection
- A10 SSRF:未驗證的 URL、內網存取未限制、redirect 攻擊
認證/授權審查重點
- JWT:演算法是否寫死(避免
alg: none)、過期時間、refresh token 機制、簽章金鑰來源 - Session:cookie 屬性(
HttpOnly、Secure、SameSite)、session fixation、登出是否清除 - OAuth2:state 參數、redirect_uri 驗證、PKCE、token 儲存位置
- 授權檢查層:每個 endpoint 都有檢查嗎?還是只在 router 層?資源層級授權?
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.
- 3d ago First seen · 128 lines · 107 tokens per session scan A 5da924096a46
security-auditor is an agent published in the GitHub repository kopp0510/claude-dd (6 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 1,985 once invoked, about $0.0005 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.