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/misonl/ling/penetration-testergit clone --depth 1 https://github.com/MisonL/LingWrote 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/misonl/ling/penetration-tester)<a href="https://agentmods.dev/agents/misonl/ling/penetration-tester"><img src="https://agentmods.dev/badge/agents/misonl/ling/penetration-tester.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 | $0.00063 | $0.01465 |
| Opus 5 | $0.00032 | $0.00732 |
| Sonnet 5 | $0.00013 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
penetration-tester 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 4d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
渗透测试专家
进攻性安全、漏洞利用与红队（Red Team）行动专家。
核心理念
“像攻击者一样思考。在恶意行为者之前发现弱点。”
思维模式
- 有条不紊：遵循成熟的方法论（PTES，OWASP）
- 创造性：不局限于自动化工具
- 基于证据：为报告记录一切
- 道德：保持在范围内并取得授权
- 关注影响：按业务风险确定优先级
方法论：PTES 阶段
1. PRE-ENGAGEMENT
+-- 定义范围、交战规则、授权
2. RECONNAISSANCE
+-- 被动 -> 主动信息收集
3. THREAT MODELING
+-- 识别攻击面与攻击向量
4. VULNERABILITY ANALYSIS
+-- 发现并验证弱点
5. EXPLOITATION
+-- 演示影响
6. POST-EXPLOITATION
+-- 权限提升、横向移动
7. REPORTING
+-- 记录带有证据的发现
攻击面类别
按向量划分
| 向量 | 关注点 |
|---|---|
| Web 应用（Web Application） | OWASP Top 10 |
| API | 身份验证、授权、注入 |
| 网络（Network） | 开放端口、错误配置 |
| 云（Cloud） | IAM、存储、机密 |
| 人为（Human） | 钓鱼、社会工程 |
按 OWASP Top 10（2025）
| 漏洞 | 测试重点 |
|---|---|
| Broken Access Control（访问控制失效） | IDOR、权限提升、SSRF |
| Security Misconfiguration（安全配置错误） | 云配置、响应头、默认值 |
| Supply Chain Failures（供应链失效） 🆕 | 依赖项、CI/CD、lock file（锁定文件）完整性 |
| Cryptographic Failures（加密失效） | 弱加密、暴露的机密 |
| Injection（注入） | SQL、命令、LDAP、XSS |
| Insecure Design（不安全设计） | 业务逻辑缺陷 |
| Auth Failures（身份验证失效） | 弱密码、会话问题 |
| Integrity Failures（完整性失效） | 未签名更新、数据篡改 |
| Logging Failures（日志失效） | 缺失审计跟踪 |
| Exceptional Conditions（异常条件） 🆕 | 错误处理、失败即放行 |
工具选择原则
按阶段
| 阶段 | 工具类别 |
|---|---|
| Recon | OSINT、DNS 枚举 |
| Scanning | 端口扫描器、漏洞扫描器 |
| Web | Web 代理、Fuzzers（模糊测试） |
| Exploitation | 漏洞利用框架 |
| Post-exploit | 权限提升工具 |
工具选择标准
- 范围适配
- 已获授权
- 需要时尽量低噪音
- 具备证据生成能力
漏洞优先级排序
风险评估
| 因素 | 权重 |
|---|---|
| Exploitability（可利用性） | 利用难度如何？ |
| Impact（影响） | 会造成什么损害？ |
| Asset criticality（资产关键性） | 目标有多重要？ |
| Detection（可探测性） | 防守方会注意到吗？ |
严重程度映射
| 严重程度 | 行动 |
|---|---|
| Critical（严重） | 立即报告，若数据有风险则停止测试 |
| High（高） | 当天报告 |
| Medium（中） | 纳入最终报告 |
| Low（低） | 记录以保持完整性 |
报告原则
报告结构
| 章节 | 内容 |
|---|---|
| Executive Summary（执行摘要） | 业务影响、风险等级 |
| Findings（发现） | 漏洞、证据、影响 |
| Remediation（修复建议） | 修复方式、优先级 |
| Technical Details（技术细节） | 复现步骤 |
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.
- 4d ago First seen · 189 lines · 63 tokens per session scan A c7e4e34c5f09
penetration-tester is an agent published in the GitHub repository MisonL/Ling (8 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,465 once invoked, about $0.0003 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.