capability-primitive-search

capability-primitive-search is a skill for Claude Code, Codex from Ed1s0nZ/CyberStrikeAI. It costs 67 tokens per session (1,304 once invoked), scanned A, original, Apache-2.0.

A method for finding attack chains by combining smaller capabilities such as reading files, writing files, making server requests, or using credentials. It treats a serious outcome as a sequence of separately gained abilities.

In plain words
What is it for?
Use it when no single issue gives code execution or another major impact, and you need to map possible combinations of access, data, configuration, and execution abilities.
Why use it?
It helps testers reason about risks that are not visible as one large flaw. It shows how lower-severity issues may combine into a more serious result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when no single issue gives code execution or another major impact, and you need to map possible combinations of access, data, configuration, and execution abilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ed1s0nz/cyberstrikeai/capability-primitive-search
About the project

CyberStrikeAI is a security operations workspace that turns natural-language plans into governed, auditable actions while recording evidence and results for later reuse. Authorized security teams use it to manage agents, tools, vulnerabilities, knowledge, and attack-chain analysis. Catalogue add-ons provide agent and skill workflows for working with the platform.

Ed1s0nZ/CyberStrikeAI · 6,410 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ed1s0nZ/CyberStrikeAI --skill capability-primitive-search
Clone the repo
git clone --depth 1 https://github.com/Ed1s0nZ/CyberStrikeAI

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for capability-primitive-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/capability-primitive-search/github.svg)](https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/capability-primitive-search)
Your own site
<a href="https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/capability-primitive-search"><img src="https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/capability-primitive-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for capability-primitive-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/capability-primitive-search"><img src="https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/capability-primitive-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01304
Opus 5 $0.00034 $0.00652
Sonnet 5 $0.00013 $0.00261
Haiku 4.5 $0.00007 $0.00130

Measured 11d ago against content hash 045689b563f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

capability-primitive-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/capability-primitive-search/SKILL.md · 49 lines

What it actually 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→
    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。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 49 lines · 67 tokens per session scan A 045689b563f5

Subscribe to this mod's changes

capability-primitive-search is a skill published in the GitHub repository Ed1s0nZ/CyberStrikeAI (6,410 stars, last pushed 15d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,304 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

fix-security-vulnerabilities-with-strix

Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use…

usestrix/strix · 124 tokens

find-security-vulnerabilities-in-code

Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy…

usestrix/strix · 129 tokens

managed-pentesting-with-strix

Run a managed pentest of a web app, API, repository, or local workspace on the app.strix.ai platform with the strix cloud CLI or REST API — no local Docker or LLM key needed. Safely review and upload local source, register assets, launch and poll scans, triage vulnerabilities, export SARIF, download compliance…

usestrix/strix · 114 tokens

ci-security-scanning-with-strix

Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…

usestrix/strix · 140 tokens

svc-mobile-android

Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.

s0ld13rr/pentestcode · 66 tokens

web-auth-bypass-idor

Broken access control - IDOR, privilege escalation, JWT abuse, mass assignment, forced browsing - for web apps and APIs. Use on any multi-user or role-based app with object IDs, tokens, or admin functionality. Triggers - /api/users/ , /orders/ , ?account=/uid=/doc=, JWT (eyJ...), role/isAdmin field, admin panel, "403…

s0ld13rr/pentestcode · 97 tokens