source-code-audit

A source-code security auditing method written in Chinese. It traces data from where it enters an application through its processing steps to dangerous operations, across languages such as PHP, Java, Python, Node.js, and Go.

In plain words
What is it for?
Use it to inspect source code for unsafe SQL, commands, file operations, deserialization, template rendering, prototype pollution, and authentication or authorization gaps.
Why use it?
It helps locate security weaknesses that may be hidden across several functions or files rather than in one obvious line. It also focuses on the conditions required to trigger a flaw and on missing permission checks.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/zhaji2333/ckskills/source-code-audit
Any agent
npx skills add zhaji2333/CkSKILLS --skill source-code-audit
Clone the repo
git clone --depth 1 https://github.com/zhaji2333/CkSKILLS

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.00794
Opus 5 $0.00037 $0.00397
Sonnet 5 $0.00015 $0.00159
Haiku 4.5 $0.00007 $0.00079

Measured 3d ago against content hash a5334ead822a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-code-audit scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

eval / exec / os.system / subprocess / pickle.loads
.agents/skills/source-code-audit/SKILL.md · 94 lines

What it actually says

source-code-audit — 源码审计专项深度挖掘

何时调用(触发条件)

  • 有源码(开源项目/泄露代码/反编译产物)
  • 用户给代码片段要求审计
  • 前端 source map 还原出完整源码
  • APK 反编译后需要审计 Java/so 层
  • 需要定位:拼接、反序列化、模板渲染、命令执行、文件操作、鉴权分支

一、静态审计方法(SAST)

核心思路

输入点 → 传播链 → 危险函数(Sink)

审计关注

  • 拼接:SQL/命令/路径/模板
  • 反序列化:unserialize/readObject/pickle
  • 模板渲染:用户输入进入模板引擎
  • 命令执行:exec/system/ProcessBuilder
  • 文件操作:上传/下载/包含/删除
  • 鉴权分支:哪些接口缺少权限校验

输出格式

  • 可疑调用链(输入 → 传播 → Sink)
  • 关键代码片段
  • 缺陷触发条件(参数、前置校验)

二、危险函数速查(按语言)

PHP

eval / assert / system / exec / passthru / shell_exec / popen
include / require / file_get_contents / unserialize
preg_replace(e修饰符) / create_function / $$变量覆盖

Java

Runtime.exec / ProcessBuilder / readObject / XMLDecoder
SpEL / OGNL / MVEL / EL表达式
JNDI lookup / JdbcRowSetImpl / TemplatesImpl

Python

eval / exec / os.system / subprocess / pickle.loads
yaml.load(Loader=Loader) / __import__ / compile

Node.js

eval / Function() / child_process / vm.runInContext
__proto__ / constructor.prototype(原型污染)

Go

os/exec.Command / text/template(SSTI)
sql拼接 / 不安全的反序列化

三、鉴权审计要点

  • 接口/路由是否有统一鉴权中间件
  • 是否存在免鉴权路径(白名单/静态资源/回调)
  • 角色判断是否可信(前端传角色 vs 服务端查库)
  • 对象级校验:是否只校验登录不校验归属
  • 管理接口与普通接口的权限边界

四、结合其他技能

审计发现的具体漏洞类型转对应技能深化:

  • 注入点 → injection-vulns
  • 反序列化 → deserialization-xxe
  • 文件操作 → file-handling
  • 鉴权缺陷 → auth-access-control
  • 加密/签名算法 → auth-access-control

五、输出与报告要点

  • 每个漏洞:输入点 / 传播链 / Sink / 缺失的校验
  • 附代码片段与触发条件
  • 可利用性评估(前置条件、影响面)
  • 修复方案(代码级)
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.

  1. 3d ago First seen · 94 lines · 75 tokens per session scan A a5334ead822a

Subscribe to this mod's changes

source-code-audit is a skill published in the GitHub repository zhaji2333/CkSKILLS (66 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 794 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…

agentscope-ai/QwenPaw · 62 tokens

xlsx

当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要:打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件(例如添加列、计算公式、格式化、制图、清理混乱数据);从头创建新的电子表格或从其他数据源创建;或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及(如"我下载目录里的 xlsx")——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件(格式错误的行、错位的表头、垃圾数据)清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…

agentscope-ai/QwenPaw · 232 tokens

terraform-cli-setup

Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装,确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置,凭证在实际使用时由 terraform-skill 引导。.

agentscope-ai/QwenPaw · 58 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

oss-upload

Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.

clacky-ai/openclacky · 40 tokens

metabigor

Use when operating the metabigor CLI for OSINT recon and infrastructure mapping without API keys. Covers finding network ranges from an ASN, org, domain, or IP (net); enumerating subdomains from certificate logs (cert); enriching IPs with ports/CVEs via Shodan InternetDB (ip); searching public GitHub code for secrets…

j3ssie/metabigor · 143 tokens