SKILLEMALL.ai
GitHub ↗ RU Sign in

CD pwn-chain

从逆向走到可用利用 (Working Exploit) 的全链路工程化方法。 适用场景：拿到了二进制 + 漏洞点 + 目标环境，需要写出一个能稳定打通的 exploit（不是只能本地复现一下、远程一打就崩的脚本）。 覆盖三大方向：栈溢出 / 堆利用 / 内核 pwn。强调"CTF 本地通 → 真实远程稳定打通"的工程差距：libc 版本错配、堆喷射时序、SMEP/SMAP/KASLR、栈对齐、远程缓冲。 核心工具链：pwntools + GEF/pwndbg + ROPgadget/Ropper + one_gadget + libc-database + qemu-system 内核调试。 触发关键词：pwn、栈溢出、堆溢出、ROP、ret2libc、ret2csu、one_gadget、libc-database、堆利用、tcache、fastbin、unsorted bin、kernel pwn、kROP、SMEP、SMAP、KASLR、modprobe_path、pwntools、GEF、pwndbg。

zhaoxuya520/reverse-skill Agent Skills author: zhaoxuya520 MIT 4 files body ≈ 1 485 tokens Open the sourcegithub.com↗ analyzed 6 d ago

从逆向走到可用利用 (Working Exploit) 的全链路工程化方法。 适用场景：拿到了二进制 + 漏洞点 + 目标环境，需要写出一个能稳定打通的 exploit（不是只能本地复现一下、远程一打就崩的脚本）。 覆盖三大方向：栈溢出 / 堆利用 / 内核 pwn。强调"CTF 本地通 →…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureGitHubSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
98
Quality 40%
76
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • low Dangerous commands cmd-privilege references/kernel-pwn.md:25
    Privilege escalation / world-writable permissions (documentation of a security skill)
    # 改 init 拿 root（CTF 学习用，真实题目通常 setuid 1000）
    security skill
  • low Dangerous commands cmd-privilege references/kernel-pwn.md:195
    Privilege escalation / world-writable permissions (code comment; documentation of a security skill)
    // 5. 利用 setuid
    commentsecurity skill

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, git, python) that frontmatter does not declare
  • 100Steps. 26 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1485 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 462: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 26 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.