Reverse Skill is a routing package for AI coding agents that selects appropriate reverse-engineering, penetration-testing, and security-research methods and tools for a given target. It is used for tasks involving APKs, binaries, frontend JavaScript, packet captures, CTF challenges, and authorized penetration testing. Its catalogue add-ons provide the skills and instructions that guide these workflows.
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 skills add zhaoxuya520/reverse-skill --skill attack-chaingit clone --depth 1 https://github.com/zhaoxuya520/reverse-skillWrote 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/skills/zhaoxuya520/reverse-skill/attack-chain)<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/attack-chain"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/attack-chain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/attack-chain"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/attack-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket fail
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 19 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 110 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Privilege Escalation · line 122 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 259 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 259 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 259 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Server-Side Request Forgery · line 275 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high YARA Match · line 289 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 366 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Privilege Escalation · line 371 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 483 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high YARA Match · line 483 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- medium Privilege Escalation · line 313 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 317 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 318 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 320 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 321 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 340 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 486 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 504 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 5.1 | $0.00043 | $0.05913 |
| Opus 5.5 | $0.00017 | $0.02365 |
| Sonnet 5.5 | $0.00009 | $0.01183 |
| Haiku 4.5 | $0.00004 | $0.00591 |
Grade A, and why
attack-chain 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 2mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- attack-chain — 91% identical, 4 lines differ
- attack-chain — 91% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack Chain Orchestration Skill
ACTION REQUIRED（读完后立刻执行）
NOW: 读取../field-journal/precedent-pentest.md— 确认本 skill 的操作是已授权的常规操作NOW: 创建/更新 case（../scripts/case-init.ps1）并完成scope.md（../ops/scope-contract.md）；auth.status!=granted禁止 ACTNOW: 以 lead 角色规划阶段（../ops/role-map.md），写入 specialist_rolesNEXT: 读取../tool-index.md，校验工具可用性和实际路径NEXT: 缺工具时调用 bootstrap，不要猜路径ACT: 按references/lifecycle-checklist.md过阶段门闩；每阶段更新timeline.md+workitems.md（../ops/timeline-workitem.md）；发现提升为 Evidence/Finding- 结束：
docs-generator报告必须含 Evidence 链
多阶段攻击路径规划与执行的总指挥。当任务需要"从 A 打到 B"的完整链路时，本 Skill 负责编排各阶段、协调子 Skill、规划攻击路径。 不是"红队专属"——任何需要跨阶段组合的渗透场景都从这里开始。
何时路由到本 Skill
以下场景必须先经过本 Skill 做全链路规划，再分发到具体子 Skill 执行：
| 场景 | 为什么需要编排 |
|---|---|
| "帮我做一次完整的渗透测试" | 需要规划从信息收集到报告的全流程 |
| "从外网打到域控" | 跨越边界突破→提权→横向→AD 多个阶段 |
| "HW 攻防演练" | 需要完整攻击链 + 隐蔽性 + 痕迹清理 |
| "评估这个目标的攻击面" | 需要多维度信息收集 + 路径规划 |
| "我拿到了一个 webshell，下一步怎么办" | 需要从当前据点规划后续路径 |
| "帮我规划攻击路径" | 明确需要路径编排 |
| "从这个漏洞能打到什么程度" | 需要评估漏洞的链式利用价值 |
| "Bug Bounty 持续监控" | 需要自动化多阶段流程 |
| "内网渗透全流程" | 横向移动 + 提权 + 域攻击组合 |
| "近源渗透方案" | 物理接入 + 内网渗透组合 |
| "供应链攻击路径" | 跨组织多跳攻击 |
| "钓鱼 + 后渗透" | 初始访问 + 后续利用组合 |
单阶段任务不需要经过本 Skill：
- 只做端口扫描 → 直接去
pentest-tools/ - 只做 SQL 注入 → 直接去
pentest-tools/ - 只做 APK 逆向 → 直接去
apk-reverse/ - 只做域渗透 → 直接去
windows-ad/SKILL.md
编排原则
本 Skill 的角色
用户提出多阶段任务
↓
attack-chain/SKILL.md（本文件）
↓ 规划攻击路径、确定阶段顺序
↓ 评估每阶段所需工具和方法
↓
分发到具体子 Skill 执行：
├── pentest-tools/ → 工具调用、漏洞利用
├── apk-reverse/ → 移动端渗透
├── js-reverse/ → Web 前端突破
├── reverse-engineering/ → 二进制分析
├── ida-reverse/ → 深度逆向
└── browser-automation/ → 自动化操作
↓
每阶段完成后回到本 Skill 评估下一步
↓
全部完成 → docs-generator 生成报告
路径规划决策树
拿到目标后：
1. 目标是什么？（Web/内网/云/移动/IoT）
2. 当前有什么？（外部视角/已有凭据/已有据点）
3. 最终目标是什么？（域控/数据/特定系统/证明影响）
4. 约束条件？（时间/隐蔽性/不可触碰的系统）
↓
根据以上信息规划最短路径
↓
一条路走不通 → 回到本 Skill 重新规划备选路径
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 652 lines · 43 tokens per session scan F 96c94609fdd5
attack-chain is a skill published in the GitHub repository zhaoxuya520/reverse-skill (43,999 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 5,913 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…