web-vuln-audit

web-vuln-audit is a skill for Claude Code, Codex from zhiyuwang720-dev/CodeAuditSkill. It costs 172 tokens per session (6,479 once invoked), scanned A, original, MIT.

A source-code security audit tool for web projects written in Go, Java, Python, PHP, or JavaScript. It checks for high- and medium-risk flaws and writes reports in the audited project’s reports/ folder.

In plain words
What is it for?
Use it to audit a web project for issues such as SQL injection, cross-site scripting, request forgery, path traversal, weak access controls, command injection, and unsafe deserialization.
Why use it?
It organizes security findings with code locations, reproduction commands, suggested fixes, and follow-up verification instead of leaving risks as unstructured notes.

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/zhiyuwang720-dev/codeauditskill/web-vuln-audit
Any agent
npx skills add zhiyuwang720-dev/CodeAuditSkill --skill web-vuln-audit
Clone the repo
git clone --depth 1 https://github.com/zhiyuwang720-dev/CodeAuditSkill

Made for: Claude Code, Codex.

Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,479 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 $0.00172 $0.06479
Opus 5 $0.00086 $0.03240
Sonnet 5 $0.00034 $0.01296
Haiku 4.5 $0.00017 $0.00648

Measured 3d ago against content hash f601e63879a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-vuln-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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Web 项目安全代码审计 skill,自动识别 Go / Java / Python / PHP / JavaScript 项目类型并加载对应漏洞清单(SQL/SSRF/XSS/CSRF/反序列化/路径穿越/鉴权/命令注入/XXE 等),输出审计报告到被审计项目的 reports/ 目录。适用于:(1) 单仓库 Web 项目的中高危漏洞扫描,(2) 自动生成可复现的漏洞报告(含代码位置、复现 curl、修复建议
skills/web-vuln-audit/SKILL.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web 项目漏洞代码审计 Skill

对 Go / Java / Python / PHP / JavaScript Web 项目进行系统化源码安全审计,输出可交付的审计报告 + 每条漏洞的并行验证报告(真实漏洞 PoC 或误判说明)。


核心约束(强制遵守)

  1. 报告输出路径 = {TARGET_PROJECT}/reports/(被审计项目根目录,不是 skill 仓库内)。主审计报告命名 {project-name}-audit-{YYYY-MM-DD}.md
  2. 只审计 High / Medium。Low 漏洞一律不写入报告(即使发现也跳过)。
  3. 审计报告必须含「项目文件树 + 审计标记」章节:全部目录到文件,仅源码文件(.go / .java / .kt / .scala / .py / .php / .js / .ts)标记 (审计) / (未审计),其他文件类型无标记。
  4. Phase 4 子 Agent 必须并行 spawn:在单次响应中通过多个 Agent 工具调用并行启动(不是串行)。
  5. PoC 验证优先真实运行:从被审计项目 README 提取 docker / docker-compose 启动指令,实际拉起环境并发送真实 HTTP 请求复现;失败再降级为静态代码证明,并在报告中显式标注「未运行验证,仅静态推理」。
  6. PoC / FP 报告命名:真实漏洞 → poc-V-{NNN}.md;误判 → fp-V-{NNN}.md,与主审计报告共存于 reports/
  7. Phase 3 主审计和 Phase 3.5 二次扫描必须遵守 Agent Contract:包括工具约束(Grep/Glob/Read,禁 Bash grep/find/cat)、Turn 预留规则(max_turns - 3 时停止探索并产出输出)。详见下方「工具使用约束」章节。

工具使用约束(Agent Contract)

以下约束适用于 Phase 3 主审计Phase 3.5 二次扫描Phase 4 子 Agent。每条规则都是强制性的。

1. 工具约束

约束 详情
搜索 必须使用 Grep(ripgrep 模式,1-3 秒)定位,Glob 匹配文件名,Read 读文件
禁止写法 Bash 中的 grep / find / cat(性能退化)
超时 Bash timeout ≤30s。Grep 超时 → 缩小 path → 连续失败 2 次 → 跳过

2. Turn 预留规则

Phase 3 主审计:
  max_turns = 30(根据项目规模调整:小项目 20,大项目 40)
  turns_used ≥ max_turns - 3 时:立即停止探索,产出结构化输出
  不得将最后 3 个 turn 用于新的 Grep/Read 探索

Phase 3.5 二次扫描:
  max_turns = 20(聚焦搜索,比对主审计少)
  turns_used ≥ max_turns - 3 时:立即停止搜索,产出结构化输出
  不得将最后 3 个 turn 用于新的 Grep/Read 探索

Phase 4 子 Agent:
  max_turns = 15(单漏洞验证,任务聚焦)
  turns_used ≥ max_turns - 3 时:立即停止验证,产出判定结果

违反 Turn 预留将导致输出丢失,整个 Agent 的发现可能被截断。

输入

用户提供(或采用默认):

  • target_project:被审计项目的根目录路径。默认为当前工作目录
  • 可选:scope(审计范围,如 internal/src/main/java/),不指定则全量。

输出

写入到 {target_project}/reports/

  • {project}-audit-{YYYY-MM-DD}.md —— 主审计报告(漏洞清单 + 文件树 + 详细发现 + 验证汇总)
  • poc-V-{NNN}.md —— 每个真实漏洞一份独立 PoC 报告
  • fp-V-{NNN}.md —— 每个误判一份误判说明

执行流程

Phase 0 — 输入解析

  1. 解析 target_project(缺省 = pwd
  2. 创建输出目录:mkdir -p {target}/reports/
  3. 记录审计起始时间,确定主报告文件名 {project}-audit-{YYYY-MM-DD}.md

Read the full file on GitHub · 419 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.

  1. 3d ago First seen · 419 lines · 172 tokens per session scan A f601e63879a7

Subscribe to this mod's changes

web-vuln-audit is a skill published in the GitHub repository zhiyuwang720-dev/CodeAuditSkill (45 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 6,479 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens