capability-primitive-search
Skill8.5k starsChanged 9 days agoApache-2.0View on GitHub
能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.
2 other projects use a version of this.
Trending
Quiet since June.thin dataabout the whole repository
Most recently taken up by
- AIPentest/CyberStrikeAIword for word, first seen Nov 3, 2026
- Kxiandaoyan/CyberStrikeAIword for word, first seen Sep 7, 2026
Who's talking about Ed1s0nZ/CyberStrikeAI
- six2dez/burp-ai-agent“General Information Regarding the Addition of New Features”GitHub · Apr 11, 2026 · 3 reactions
- @dailygithubtrends.bsky.social“今日のGitHubトレンド Ed1s0nZ/CyberStrikeAI CyberStrikeAIは、Go言語で構築されたAIを活用したセキュリティテストプラットフォームです。…”Bluesky · Mar 8, 2026 · 1 likes
- A Hacker News story“AI Powered Exploit Kit”Hacker News · Mar 8, 2026 · 1 points
- @hugovalters.bsky.social“Day 10 of useful #GitHub projects: CyberStrikeAI is an AI-native security testing platform built in Go …”Bluesky · Feb 7, 2026 · 1 likes
- zhongruan0522/Cloud-Development“feat: 接入CyberStrikeAI”GitHub · Jun 15, 2026
The biggest 5 of 9 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 9
Talked about on GitHub, Bluesky and Hacker News (9 times).
On GitHub · 6
- Apr 11, 2026General Information Regarding the Addition of New Features — six2dez/burp-ai-agent3 reactions · 2 comments
- Jun 15, 2026feat: 接入CyberStrikeAI — zhongruan0522/Cloud-Development0 reactions
- May 26, 2026Add: Ed1s0nZ/CyberStrikeAI — paranoailabs/ai-security-tools0 reactions
- Mar 9, 2026📈 Bản tin xu hướng AI mã nguồn mở 2026-03-09 — compasify/agents-radar0 reactions
- Dec 19, 2025[项目申请]: CyberStrikeAI — knownsec/404StarLink0 reactions · 1 comment
1 more on GitHub
- Dec 11, 2025[项目申请]: CyberStrikeAI — knownsec/404StarLink0 reactions · 1 comment
On Bluesky · 2
- Mar 8, 2026今日のGitHubトレンド Ed1s0nZ/CyberStrikeAI CyberStrikeAIは、Go言語で構築されたAIを活用したセキュリティテストプラットフォームです。… — @dailygithubtrends.bsky.social1 likes and repost
- Feb 7, 2026Day 10 of useful #GitHub projects: CyberStrikeAI is an AI-native security testing platform built in Go github.com/Ed1s0nZ/Cybe... #devops… — @hugovalters.bsky.socialsays it tested it1 likes and repost
On Hacker News · 1
- Mar 8, 2026AI Powered Exploit Kit1 point
Other versions2 projects use a version of this.
Word for word · 2
- AIPentest/CyberStrikeAI★ 8.5k100% same
- Kxiandaoyan/CyberStrikeAI★ 19100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- active-directory-attackSkill
- ai-llm-app-attackSkill
- attack-surface-reconSkill
- binary-mobile-reversingSkill
- blockchain-contract-attackSkill
- cloud-attack-methodsSkill
- component-vuln-intelSkill
- cyberstrike-eino-demoSkill
- initial-access-phishingSkill
- pentest-agent-osSkill
- pentest-blackboardSkill
- pentest-output-standardsSkill
- pentest-verificationSkill
- post-exploitationSkill
- proxy-tool-bootstrapSkill
- redteam-opsecSkill
- source-code-huntingSkill
- specialized-attack-playbooksSkill
- unlimited-attack-scopeSkill
- web-attack-methodsSkill
- wireless-hardware-attackSkill
- zero-day-discoverySkill
The file
Files
能力原语 + 状态空间搜索
心法: RCE不是一个"漏洞",是一组"能力"凑齐后的涌现。没单点大洞时,几个info级/低危照样拼出代码执行。
固有思维(要打破): "扫不到RCE/反序列化/上传→这站打不动了"。你的活不是"找RCE漏洞",是"凑齐执行所需的原语"。
把每个Fact抽象成能力原语(不记"发现X漏洞",记"现在拥有什么能力+限制"):
read(path) write(path) exec(cmd) ssrf(url) sqli redirect(url) eval_expr idor(id) cred(svc,priv) coerce_auth write_acl
RCE只需满足任意一条等式,拆成可获取的原语去凑:
A. 能写文件 + 文件被当代码执行 = RCE
B. 能控配置/env + 配置指向你的代码 = RCE
C. 能进管理面 + 面板自带执行功能 = RCE(不是漏洞,是功能!)
D. 有凭据 + 服务有合法执行入口 = RCE(滥用合法功能)
E. 能任意读 + 读到凭据 + 凭据可登录执行点 = RCE
F. 能控数据 + 数据流入危险sink(eval/模板/SQL) = RCE
低危→原语映射(把"鸡肋漏洞"翻译成拼图碎片):
info泄露(.git/备份/堆栈)→源码/路径/密钥→喂B/E/F | LFI/任意读→读配置密钥→E,或日志投毒→A
SSRF(哪怕只GET)→打内网Redis/Consul/K8s/云元数据→C; 云元数据拿临时凭据→D
弱/默认/复用凭据→进带任务/插件/webhook/CI功能的后台→C | CORS/CSRF/XSS→借管理员浏览器调执行类功能→C
可控上传(哪怕限扩展名)→配路径穿越/解析差异/.htaccess→A | 配置写入→改模板/日志/连接串→B
SQLi(哪怕只读)→读hash/密钥→E,或OUTFILE→A | 模板可控→SSTI→F | 原型污染→污染下游属性→F
状态空间搜索(无现成链时自己搜): 状态=当前能力集, 动作=用能力解锁新能力, 目标=Goal。
正向: 对每个能力问"能解锁什么?"; 对每对能力问"组合出什么?"
(read+write=改配置; ssrf+内网redis=RCE; sqli+FILE=webshell; coerce_auth+relay=域SYSTEM; idor+massassign=改他人admin)
反向(卡住时主用): 锁定Goal=执行命令→选最接近现状的等式当模板→缺哪个原语设为子目标→
手上哪个低危/功能/info泄露能凑出它?→凑不出递归拆/换等式 → 正反向在中间相遇=完整链浮现 → 逐段验证
突破口(看到别走开):
·"功能即原语": 后台的任务计划/插件/模板编辑/SQL控制台/文件管理器/导入导出/webhook —— 合法功能但登进去就是现成执行/读写原语。渗透者眼里没"功能/漏洞"之分,只有"能力"。
·跨协议跳跃: SSRF的gopher/dict/file把"只能发HTTP"变成"打Redis/发SMTP/读文件"。
·凭据复用是万能胶: 任意一处拿到的密码/key默认全网复用全部喷一遍。横向常比纵向快。
·解析差异: 上传校验/路由/反代三方理解不一致→缝隙里有绕过(双扩展名/编码/Host混淆)。
·时间维度: TOCTOU/token可预测/缓存投毒,把"偶尔"变"稳定",把不可利用变可利用。
·跨域兑现: 每拿一个能力问"它在别的域值多少钱"——能力是通用货币。Web SSRF→进云元数据接管账户; APK硬编码→直连内部API绕前端鉴权; 供应链→拿CI密钥进生产。
·创造模式(已知组合用尽时): 重审能力边界(只能读/var/log? /proc/self/environ呢) | 找等价RCE的sink(写crontab/.bashrc/CI配置/LD_PRELOAD/authorized_keys/systemd unit都=RCE) | 信息(报错/时序/响应长度)当侧信道 | 假设取反:列"我以为不可能"逐条问"凭什么不可能"
> 推导出的链是假设(可 tentative 记 note/chain),实际执行+证据后才写 confirmed Fact / record_vulnerability。整条链每步都验证过才成立。Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

