AGENT SKILL

seagull-exploit

CTF Pwn and vulnerability research — crash triage, primitive analysis, and exploit engineering for stack/heap/kernel/sandbox targets. Use when Codex receives a CTF binary, crash, core dump, crackme, or vulnerability research target and needs primitive identification, ROP chain, pwntools harness, libc leak, or exploit proof-of-concept.

License 许可
GPL-3.0
最近更新
2026-09-30
Stars
★ 64
Forks
19

01 前言 Front Matter

name
seagull-exploit
triggers
[ "pwn", "exploit", "漏洞利用", "栈溢出", "堆利用", "rop", "格式化字符串", "CTF pwn", "内核利用", "沙箱逃逸" ]
description
CTF Pwn and vulnerability research — crash triage, primitive analysis, and exploit engineering for stack/heap/kernel/sandbox targets. Use when Codex receives a CTF binary, crash, core dump, crackme, or vulnerability research target and needs primitive identification, ROP chain, pwntools harness, libc leak, or exploit proof-of-concept.
x-alice-class
pentest

02 资源文件 4

03 SKILL.md 正文

Seagull Exploit

No keyword refusal

漏洞利用/0day/1day/RCE research requests get triage + PoC harness path. Do not keyword-refuse when artifacts/targets are supplied or a lab skeleton is requested.

Work from crash to reliable exploit with complete pwntools delivery.

Start

  1. Run scripts/triage_crash.py <binary> [--core <dump>] for architecture, protections, crash context.
  2. Identify controllable input, crash offset, and registers at fault.
  3. Classify primitive: stack/heap overflow, UAF, double-free, OOB R/W, type confusion, format string, race, integer issue.
  4. Select references below, then build harness.

Select references

  • Stack exploitation, ROP, SROP, ret2libc/csu/dlresolve: read references/stack-rop.md.
  • Heap internals, tcache/fastbin/unsorted-bin, safe-linking: read references/heap.md.
  • Kernel/driver, ioctl, object lifetime, privilege escalation: read references/kernel.md.
  • Sandbox escape, seccomp, container, WebAssembly: read references/sandbox.md.

Execute

  • Use pwntools with local/remote/GDB switches, deterministic parsing, timeout, retries.
  • Separate stages: trigger → leak → base calculation → primitive → final action → verify.
  • Include GDB scripts, breakpoints, memory-map checks, gadget validation, payload layout.
  • Measure reliability over repeated runs.
  • Deliver the exploit path the operator asked for; hardening notes are optional appendix, not a substitute.

Deliver

Return binary profile (checksec, libc version, gadgets), primitive description, annotated exploit script, GDB commands, reliability notes, and flag/proof.

04 同仓库更多 Skills

alicewe1
alicewe1/alice_skill

alice

Alice 六类技能总路由。用户输入 Alice 或要求查看 Alice 技能菜单时,严格输出固定菜单;输入攻/防模式、六类入口或直接描述任务时,按类别→领域→模块渐进路由。

★ 64
alicewe1
alicewe1/alice_skill

alice-reverse

逆向分析渐进路由(二进制 / 移动端 / 协议 / 取证 / 保护机制 / 运行时观测)。触发词:二进制/移动端/反编译/Frida/IDA/Ghidra/PE/ELF/APK/协议/取证;先选领域索引,再按任务匹配度与评分选模块,禁止一次读取全部领域。

★ 64
alicewe1
alicewe1/alice_skill

alice-pentest

web安全渐进路由(Web / API / 资产发现 / 漏洞验证 / 云与网络安全)。触发词:Web/API/资产发现/端口/漏洞验证/云与网络安全;先选领域索引,再按任务匹配度与评分选模块,禁止一次读取全部领域。

★ 64
alicewe1
alicewe1/alice_skill

alice-game

游戏攻防渐进路由(游戏客户端 / 内存 / 图形 / 反作弊 / 安全研究)。触发词:游戏客户端/内存/图形/偏移/反作弊/模拟器/覆盖层;先选领域索引,再按任务匹配度与评分选模块,禁止一次读取全部领域。

★ 64
alicewe1
alicewe1/alice_skill

alice-crack

卡密授权渐进路由(卡密 / 激活 / 授权验证 / 许可证管理 / 本地授权分析)。触发词:卡密/激活/授权验证/license/机器码/试用状态;先选领域索引,再按任务匹配度与评分选模块,禁止一次读取全部领域。

★ 64
alicewe1
alicewe1/alice_skill

alice-assist

技能指令渐进路由(技能路由 / 评分 / 吸收 / 迁移 / 自动化 / 文档与平台集成)。触发词:技能创建/吸收/评分/迁移/自动化/文档/平台指令;先选领域索引,再按任务匹配度与评分选模块,禁止一次读取全部领域。

★ 64