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 skills/auroraproudmoore/java-audit-skill/java-audit-skillnpx skills add AuroraProudmoore/java-audit-skill --skill java-audit-skillgit clone --depth 1 https://github.com/AuroraProudmoore/java-audit-skillWhat 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 | $0.00184 | $0.22915 |
| Opus 5 | $0.00092 | $0.11458 |
| Sonnet 5 | $0.00037 | $0.04583 |
| Haiku 4.5 | $0.00018 | $0.02292 |
Grade A, and why
java-audit-skill 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 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.
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 — 2,111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI+Java/前端 代码审计 Skill
本 Skill 将资深审计员的工作方法和质量标准编码成 LLM 可执行的协议，解决裸跑 LLM 覆盖率低、幻觉高、优先级混乱等核心痛点。
支持的语言类型
| 语言类型 | 框架支持 | 主要检查内容 |
|---|---|---|
| Java/Kotlin | Spring、Spring Boot、Struts、Jersey、Dubbo、gRPC | 反序列化、SQL注入、命令执行、认证绕过、SSRF、文件操作 |
| JavaScript/TypeScript | 原生、Node.js | XSS、代码注入、原型污染、敏感信息泄露 |
| React | React 16+、Next.js | dangerouslySetInnerHTML、href注入、SSR XSS |
| Vue | Vue 2/3、Nuxt.js | v-html XSS、模板注入、不安全渲染 |
| 混合项目 | 前后端分离 | 后端API安全 + 前端XSS/配置安全 |
脚本架构
⚠️ 重要：脚本已按语言类型拆分，职责清晰
scripts/
├── audit.py # 通用入口（语言检测 + 路由分发）
├── java_audit.py # Java/Kotlin 后端审计
└── frontend_audit.py # JavaScript/React/Vue 前端审计
脚本职责
| 脚本 | 职责 | 包含功能 |
|---|---|---|
| audit.py | 通用入口 | 语言检测、路由分发、统一参数解析 |
| java_audit.py | Java 审计 | Java Tier 分类、Java 危险模式、EALOC 计算、覆盖率检查 |
| frontend_audit.py | 前端审计 | 前端 Tier 分类、前端危险模式、依赖检查、配置安全 |
调用流程
用户执行: python audit.py /path/to/project --scan --tier
↓
[audit.py]
↓
语言检测: detect_project_language()
↓
┌───────────────┼───────────────┐
│ │ │
java react/vue mixed
│ │ │
↓ ↓ ↓
[java_audit.py] [frontend_audit.py] [两者都执行]
使用方法
# 自动检测语言并执行审计
python scripts/audit.py /path/to/project --scan --tier
# Java 项目审计（直接调用）
python scripts/java_audit.py /path/to/java-project --scan --tier
# 前端项目审计（直接调用）
python scripts/frontend_audit.py /path/to/frontend-project --language react --scan --tier
核心理念
LLM 有能力，缺纪律。 Skill 不教 LLM "什么是 SQL 注入"，而是给它装上资深审计员的工作骨架——定义工作流、分配资源、设置护栏、标准化输出。
6 阶段审计流水线
Phase 0 → Phase 1 → Phase 2 → Phase 2.5 → Phase 3 → Phase 5 → Phase 4（可选）
代码度量 项目侦察 多层审计 覆盖率门禁 漏洞验证 标准化报告 规则沉淀
每个 Phase 有明确的输入、输出和质量标准，中间结果全量持久化到文件。
⚠️ Phase 编号说明：
- Phase 0-3：核心审计流程（必须执行）
- Phase 5：标准化报告（在验证后生成）
- Phase 4：规则沉淀（可选，在报告后执行）
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 · 2,111 lines · 184 tokens per session scan A 5f8a7b62e84f
java-audit-skill is a skill published in the GitHub repository AuroraProudmoore/java-audit-skill (24 stars, last pushed 3mo ago), licensed MIT. It adds 184 tokens to every session and 22,915 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
union-type-wrappers
Add typed getters and setters over BinaryData properties that represent TypeSpec union types in generated Java models. Use when generated classes expose BinaryData for union-typed fields and you need ergonomic, type-safe accessors instead.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
run-tests
Run project tests using Maven (mvn). Use when the user asks to run tests.
search-m2
Search for Java classes inside Maven dependencies in /.m2. Use when the user asks to locate classes or inspect JARs. Cross-reference pom.xml files in the current directory to resolve dependency names/versions.
using-process-tool
Describes how to correctly use 'process' tool.