zero-day-discovery
0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.
Skill by Kxiandaoyan
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kxiandaoyan-zero-day-discovery
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
zero-day-discovery- Description
- 0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.
- License
- Apache-2.0
- Instructions
- 24 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## 0day 自主发现引擎(全网搜不到漏洞时自己挖)
```
核心转变: 从"匹配已知漏洞库"→"理解代码/协议怎么工作,推断它哪里会坏"。0day不是运气,是方法。
五条主路:
1.变体分析(最高产): 拿一个CVE补丁→提炼漏洞模式→全库grep同模式其它位置→补丁没覆盖的=0day
2.补丁间隙: 读补丁过滤逻辑,黑名单几乎总能绕(漏了某种编码/等价函数/别名)→新CVE
3.差分测试: 两组件对同一输入理解不一致(WAF vs 后端/校验器 vs 执行器)→走私/SSRF绕过
4.Fuzzing: 写harness(包住处理不可信输入的函数)+造语料/字典+崩溃triage(可复现/可控/可利用性)
AFL++/libFuzzer(覆盖率引导找内存破坏) boofuzz(协议) radamsa(黑盒) restler(REST API)
5.污点推理(有源码最强): source(参数/Header/反序列化字段)无有效sanitizer到sink(exec/SQL/模板)=0day
CodeQL写query自动求数据流可达 / Semgrep / Joern
N-day武器化(advisory出了但全网无PoC): 从补丁diff逆向重建exploit(bindiff/diaphora二进制对比,
厂商regression test常就是PoC雏形)→本地试验场调通→打目标。漏洞窗口期最大化,红队最值钱能力之一。
猎人思维(看任何代码/端点/协议逐层逼问,每个"是"都是0day候选):
信任边界:假设输入可信吗?什么情况不成立? | 状态时序:两步间状态能改吗(TOCTOU)?能打乱顺序吗?
解析规范化:解析几次?normalize在校验前还是后? | 边界极值:负数/0/超大/类型混淆/编码/null字节?
隐含能力:这功能"顺便"给了我什么? | 唯一性:ID/token可预测吗?"秘密"真是秘密吗?
把组件变"假设清单"逐个打破: 文件上传隐含假设"只传图片/扩展名可信/文件名不含路径/内容只是数据"→逐个打破=漏洞,组合=链。
0day验证(比CVE要求更高): 可复现(最小PoC)+根因清楚(哪行/哪个假设)+影响可证(实际读写执行)+排除误报。
```From Kxiandaoyan/CyberStrikeAI, Apache-2.0.
More from Kxiandaoyan/CyberStrikeAI
- 0.612score
experience-closeout
Kxiandaoyan
收尾时把可复用方法论交给系统经验草稿,而不是手写 SKILL.md。 Use when a project/queue/conversation is wrapping up and the user asks to summarize lessons; facts and vulns must already…
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
component-vuln-intel
Kxiandaoyan
识别组件后先查本机近5年CVE语料(zvec),无命中或需在野/分析长文再联网。 Use when a framework/component/version is identified; local corpus first, then public search.
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
handoff-persistence-c2
Kxiandaoyan
CS 内置 C2 没有目标侧自启动和长期维权。Beacon 会话一旦在线,按设置页已保存的下载地址投递运维方在自己维权 C2 上生成好的 Agent,再按主机名+新出现判定上线,然后不再使用该信道。 Use when a CyberStrikeAI Beacon session is online and…
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
local-corpus-cve
Kxiandaoyan
在本机近5年CVE语料仓(zvec)中检索编号、产品与CNA描述。 Use when the user mentions CVE-IDs, a vendor/product/version, or asks what known issues exist before searching the public web.
SkillBFreshness: B★ 33Claude Code +9 - 0.587score
find-skills
Kxiandaoyan
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillBFreshness: B★ 33Claude Code +9
Signals
- Stars
- 33
- Forks
- 11
- Open issues
- 0
- Last commit (this folder)
- Sep 7, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Kxiandaoyan/CyberStrikeAI
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.851score
zero-day-discovery
AIPentest
0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.
SkillAFreshness: A★ 8KClaude Code +9 - 0.381score
zero-day-discovery
langbyyi
0day自主发现引擎:变体分析/补丁间隙/差分/Fuzzing/污点推理/N-day武器化/猎人思维。Use when public vulns not found and need to discover 0day or weaponize N-day.
SkillAFreshness: A★ 131Claude Code +9
More from Kxiandaoyan
- 0.612score
experience-closeout
Kxiandaoyan
收尾时把可复用方法论交给系统经验草稿,而不是手写 SKILL.md。 Use when a project/queue/conversation is wrapping up and the user asks to summarize lessons; facts and vulns must already…
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
component-vuln-intel
Kxiandaoyan
识别组件后先查本机近5年CVE语料(zvec),无命中或需在野/分析长文再联网。 Use when a framework/component/version is identified; local corpus first, then public search.
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
handoff-persistence-c2
Kxiandaoyan
CS 内置 C2 没有目标侧自启动和长期维权。Beacon 会话一旦在线,按设置页已保存的下载地址投递运维方在自己维权 C2 上生成好的 Agent,再按主机名+新出现判定上线,然后不再使用该信道。 Use when a CyberStrikeAI Beacon session is online and…
SkillBFreshness: B★ 33Claude Code +9 - 0.612score
local-corpus-cve
Kxiandaoyan
在本机近5年CVE语料仓(zvec)中检索编号、产品与CNA描述。 Use when the user mentions CVE-IDs, a vendor/product/version, or asks what known issues exist before searching the public web.
SkillBFreshness: B★ 33Claude Code +9 - 0.587score
find-skills
Kxiandaoyan
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillBFreshness: B★ 33Claude Code +9
Cite this page
zero-day-discovery skill. Agent Mart. https://agentmart.dev/skills/kxiandaoyan-zero-day-discovery (last updated 2026-10-24)