capability-primitive-search SKILL.md skillA

capability-primitive-search from aipentest/cyberstrikeai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aipentest/cyberstrikeai/capability-primitive-search@git:20260729.8882d70

Pins git:20260729.8882d70 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aipentest/cyberstrikeai
Path
skills/capability-primitive-search/SKILL.md
Versions recorded
2
Latest version
git:20260729.8882d70, committed Jul 29, 2026
First version recorded
Jul 21, 2026
Size
4,107 bytes
Repository stars
7,963
License
Apache-2.0

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## 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→
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aipentest/cyberstrikeai/capability-primitive-search@sha256:045689b563f5610c

The line at the top of this page pins the label git:20260729.8882d70, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_kvlrehe3rgnydwks.svg)](https://markdownregistry.com/a/art_kvlrehe3rgnydwks)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 21, 2026 and Jul 29, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260729.8882d70 latest2026-07-29 8882d70 4,107 BA view · diff
git:20260721.2b63e3b2026-07-21 2b63e3b 4,095 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4107 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

aipentest/cyberstrikeai · 7,963 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kvlrehe3rgnydwks
GET https://markdownregistry.com/api/v1/resolve?ref=aipentest/cyberstrikeai/capability-primitive-search
GET https://markdownregistry.com/api/v1/blob/045689b563f5610ca505e1d2d870a0e635087a8a5864c926ade82bde28a227e4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from aipentest/cyberstrikeai

find-skills SKILL.md skill
aipentest/cyberstrikeai · mcp-servers/pent_claude_agent/.claude/skills/find-skills/SKILL.md · Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is…
git:20260317.1d505b7 · audit A · 7,963 stars
active-directory-attack SKILL.md skill
aipentest/cyberstrikeai · skills/active-directory-attack/SKILL.md · 内网域攻击:BloodHound,Kerberoast,ADCS ESC1/ESC8,NTLM Relay,Coerce,DACL,DCSync,Zerologon/NoPac/PrintNightmare,mitm6,LLMNR,Linu…
git:20260729.8882d70 · audit A · 7,963 stars
ai-llm-app-attack SKILL.md skill
aipentest/cyberstrikeai · skills/ai-llm-app-attack/SKILL.md · AI/LLM应用攻击:提示注入,Agent工具滥用RCE,RAG投毒,MCP供应链,torch.load pickle RCE。Use when testing LLM apps, agents, RAG, MCP plugins, or…
git:20260729.8882d70 · audit A · 7,963 stars
attack-surface-recon SKILL.md skill
aipentest/cyberstrikeai · skills/attack-surface-recon/SKILL.md · 侦察/攻击面测绘:被动whois/amass/crt.sh/FOFA/Shodan,主动subfinder/httpx/naabu/katana/nuclei,DNS地域/CDN/Nginx…
git:20260729.8882d70 · audit A · 7,963 stars
binary-mobile-reversing SKILL.md skill
aipentest/cyberstrikeai · skills/binary-mobile-reversing/SKILL.md · APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native…
git:20260729.8882d70 · audit A · 7,963 stars
blockchain-contract-attack SKILL.md skill
aipentest/cyberstrikeai · skills/blockchain-contract-attack/SKILL.md · 区块链/智能合约:Etherscan,slither/mythril,重入/访问控制/预言机/闪电贷,跨链桥,RPC暴露。Use when auditing smart contracts, DeFi, or blockchain…
git:20260729.8882d70 · audit A · 7,963 stars
cloud-attack-methods SKILL.md skill
aipentest/cyberstrikeai · skills/cloud-attack-methods/SKILL.md · 云攻击:元数据API,S3/K8s,AWS/Azure/GCP身份提权,MinIO矩阵,阿里云FC,ChengZi SDK解密。Use when attacking cloud metadata, IAM, K8s, MinIO…
git:20260729.8882d70 · audit A · 7,963 stars
component-vuln-intel SKILL.md skill
aipentest/cyberstrikeai · skills/component-vuln-intel/SKILL.md · 联网情报收集:识别组件后必做CVE/搜索引擎/中文社区/GitHub PoC/资产引擎/即时情报/依赖扩展+受阻换路。Use when a framework/component/version is identified and…
git:20260729.8882d70 · audit A · 7,963 stars
cyberstrike-eino-demo SKILL.md skill
aipentest/cyberstrikeai · skills/cyberstrike-eino-demo/SKILL.md · 满配示例技能包:SKILL.md + scripts/、references/、assets/ 等可选目录;验证 Eino skill 与 HTTP 包内路径(仅授权安全测试与教学)。
git:20260721.2b63e3b · audit B · 7,963 stars
initial-access-phishing SKILL.md skill
aipentest/cyberstrikeai · skills/initial-access-phishing/SKILL.md · 初始访问/钓鱼/社工:凭据喷洒,AiTM,设备码,OAuth同意钓鱼,载荷,vishing。Use when needing initial access, phishing, AiTM, device code, or social…
git:20260729.8882d70 · audit A · 7,963 stars
pentest-agent-os SKILL.md skill
aipentest/cyberstrikeai · skills/pentest-agent-os/SKILL.md · 渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法…
git:20260729.8882d70 · audit A · 7,963 stars
pentest-blackboard SKILL.md skill
aipentest/cyberstrikeai · skills/pentest-blackboard/SKILL.md · CyberStrikeAI 项目黑板:跨会话 Fact 图(SQLite)+ upsert_project_fact/record_vulnerability 边渗透边记录节奏、关系边…
git:20260729.8882d70 · audit A · 7,963 stars

Every file in aipentest/cyberstrikeai

Browse by kind, by grade A, or by owner.