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 xAmirHamza77/ReverseOps-Skill --skill pwn-chaingit clone --depth 1 https://github.com/xAmirHamza77/ReverseOps-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/xamirhamza77/reverseops-skill/pwn-chain)<a href="https://agentmods.dev/skills/xamirhamza77/reverseops-skill/pwn-chain"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/pwn-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/xamirhamza77/reverseops-skill/pwn-chain"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/pwn-chain.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00258 | $0.02989 |
| Opus 5 | $0.00129 | $0.01494 |
| Sonnet 5 | $0.00052 | $0.00598 |
| Haiku 4.5 | $0.00026 | $0.00299 |
Grade A, and why
pwn-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 6d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACTION REQUIRED(读完后立刻execute)
NOW: read../field-journal/precedent-reverse.md— 确认本 skill 的operation是已authorization的常规operationNOW: 确认当前task是否hit本 skill 的适用scopeNEXT: read../tool-index.md,checksumtoolavailable性和实际pathNEXT: 缺tool时调用 bootstrap,不要猜pathACT: 进入"工作流"第一步并execute,不要停在确认status
从vulnerability点到 Working Exploit (Pwn Chain)
适用scope
当task属于以下scenario时使用本 skill:
- 拿到二进制 + 已知vulnerability点 — 静态/审计/fuzz 已经找到溢出/UAF/double free,需要从触发到拿 shell
- CTF 题已经本地通了,远程打不通 — 远端environment差异导致script失效,需要稳定化
- 真实target的二进制利用 — SRC / red teamscenario下,已经识别到memory损坏vulnerability,需要构造 RCE
- Linux kerneldriver的 ioctl bug — 用户态触发,target是privilege escalation到 root
前提:你已经知道"哪里炸了"。本 skill 不负责findingvulnerability(那是 fuzzing / 审计),只负责"从vulnerability点写出 exploit"。
与其他 skill 的分工
| scenario | 用什么 |
|---|---|
| 识别 custom VM / anti-debug / 复杂 obfuscation | reverse-engineering/ |
| 从零打开二进制做static analysis | ida-reverse/ 或 radare2/ |
| 有vulnerability点,写 exploit 打通远程 | 本 skill |
| 把 pwn 拿到的 shell 整合进完整attack chain | attack-chain/(下游) |
reverse-engineering/ 关注"理解程序在干什么"(模式识别、protocol还原、解 CTF 题里的奇怪机制);本 skill 关注"把已经看懂的vulnerability变成可execute的攻击"。两者经常配套使用,但分工清晰。
核心工作流
Step 1: 确认vulnerability类型 + 保护机制
├─ checksec ./vuln(NX / Canary / PIE / RELRO / Fortify)
├─ file ./vuln + readelf -d ./vuln
├─ vulnerability分类:栈溢出 / 格式化字符串 / heap (UAF/DF/OF) / 整数 / 竞态 / kernel
└─ → 决定走哪个 references/
Step 2: 选择利用policy
├─ NX 关 + 无 ASLR → 直接 shellcode
├─ NX 开 + 给 libc → ret2libc / one_gadget
├─ NX 开 + 不给 libc → leak 后 libc-database 反查
├─ heap → 按 glibc version对应技术 (tcache/fastbin/unsorted/large)
└─ kernel → commit_creds / modprobe_path / core_pattern
Step 3: 准备 libc + gadget
├─ libc-database:./find puts 0x6f0
├─ ROPgadget --binary ./libc.so.6 --only "pop|ret"
├─ one_gadget ./libc.so.6
└─ 计算 base:leak_addr - libc.sym['puts']
Step 4: 写 pwntools template(本地 process)
├─ context.binary = ELF('./vuln')
├─ p = process('./vuln') / p = gdb.debug('./vuln','b *main+xx')
├─ payload = cyclic(N) + p64(ret) + ...
└─ p.interactive()
Step 5: 本地通
├─ 反复 attach + 看寄存器 + 调 offset
├─ 用 pwndbg/GEF 的 vmmap / heap / bins / telescope
└─ 跑通后切 remote()
Step 6: 远程稳定化
├─ libc 偏移:用 leak 反查 libc-database,不要拍脑袋
├─ 栈对齐:16-byte 不对齐 → movaps 崩 → 加一个 ret gadget
├─ 远程network延迟 → recvuntil 精确锚字符串,禁用模糊 sleep
├─ 远程缓冲:sendlineafter 比 sendline 更稳
├─ heap喷success率:放大 spray 数量 + 留 padding chunk 防合并
└─ 多次跑:写 while True 验证success率 ≥ 95%
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.
- 6d ago First seen · 193 lines · 258 tokens per session scan A d1c213bb85e5
pwn-chain is a skill published in the GitHub repository xAmirHamza77/ReverseOps-Skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 258 tokens to every session and 2,989 once invoked, about $0.0013 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 2026-09-03.
Other skills, from other repositories
interacting-with-project-runtime
Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.
using-gradle
Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.
debug-helper
Systematic debugging approach for identifying and fixing issues.
error-handling
Read the error codes these tools raise and decide whether to retry, fix the call, or stop.
wcode
Use the wcode plugin and its MCP tools for repository coding, review, debugging, refactoring, architecture, Graph/Design inspection, safe edits, command execution, and verification. Trigger whenever wcode is installed or named, even when its tools are lazily registered or omitted from the host's initial tool list.
inversion
"Invert, always invert." Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve problems by thinking backward from failure. Use when: Goal setting - Define what would guarantee failure, then avoid it; Risk analysis - Identify what could destroy your project before starting; Decision…