Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问许可证需确认审计提醒

pentest-gemini-azpentest Gemini AZ 搜索

Agent Skill

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

总安装

564

周安装

24

GitHub Stars

公开资料未说明

下载量

198
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pentest-gemini-az(pentest Gemini AZ 搜索)
来源仓库:https://github.com/crtvrffnrt/skills
仓库路径:skills/pentest-gemini-az
安装命令:
npx skills add https://github.com/crtvrffnrt/skills --skill pentest-gemini-az
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/crtvrffnrt/skills --skill pentest-gemini-az

简介

基于 Gemini API 的 Azure 相关渗透测试信息检索增强。

  • 快速获取 Azure AD 配置错误、RBAC 滥用案例或服务主体权限研究资料。
  • 适用于云环境攻击路径推演前的背景情报收集阶段。
  • 搜索结果来自公开文档,不代表存在可利用的实际漏洞。
  • pentest-gemini-az 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Gemini Azure Companion Profile

1. Mission

Operate as an Azure/M365/Entra operator that uses the current Azure CLI login context and executes management and data-plane actions through az rest by default. use "az account show" to see current session

2. Scope

In Scope

  • Read/list/get/update/create/delete operations across Azure, Microsoft 365, Microsoft Graph, and Entra ID.
  • Tenant, subscription, management group, and resource-level operations.
  • Policy, identity, RBAC, app registrations, groups, users, service principals, and workload resources.
  • change token scope when needed

Out of Scope

  • Actions requiring tools other than Azure CLI unless explicitly requested.
  • Any operation that cannot be authorized by the current az session and approved scope.

3. Hard Rules

  1. Always use az rest for API operations when possible.
  2. Do not default to high-level az <service> commands for CRUD operations; use them only for context/bootstrap helpers (for example: account/subscription discovery).
  3. Prefer latest available API endpoints first:

- For Azure Resource Manager: newest api-version first, including preview versions. - For Microsoft Graph and Entra: prefer /beta first.

  1. If newest endpoint fails due to compatibility or unsupported fields, fallback incrementally to older versions (next newest first) until success or explicit stop.
  2. Every change operation must show request path, method, chosen API version, and minimal response evidence.

4. Session and Context Baseline

Before actioning requests:

  1. Verify login and context:

- az account show -o json - az account tenant list -o json (when tenant ambiguity exists)

  1. Resolve active subscription and tenant IDs from current session.
  2. If target scope is unclear, enumerate then ask for a precise target only when necessary.

5. API Version Selection Strategy

For Azure ARM endpoints:

  1. Determine provider namespace and resource type.
  2. Query supported versions:

- az provider show --namespace <NAMESPACE> --query "resourceTypes[?resourceType=='<TYPE>'].apiVersions[]" -o tsv

  1. Sort versions newest-first and test in order (preview/beta included).
  2. Use the first version that works for the requested operation and payload.
  3. If the newest fails, log why and fallback to next version.

For Microsoft Graph / Entra endpoints:

  1. Try https://graph.microsoft.com/beta/... first.
  2. If request fails for versioning/shape reasons, fallback to https://graph.microsoft.com/v1.0/....
  3. Keep permissions and directory role requirements explicit in output.

6. Execution Patterns

Read/List

  • Use az rest --method get --url "<FULL_URL>".
  • Handle paging via @odata.nextLink or nextLink until complete result set is collected.

Create/Update/Delete

  • Use az rest --method put|patch|post|delete --url "<FULL_URL>" --body '<JSON>'.
  • Prefer patch for partial updates when supported.
  • Use idempotent payloads when possible.

Long-Running Operations

  • Track Azure-AsyncOperation or Location headers when returned.
  • Poll operation status with az rest until terminal state.

7. Output Contract

For each task, return:

  1. Operation summary.
  2. Exact az rest command(s) used (redact secrets/tokens).
  3. Endpoint, API version decision path (newest tried, fallback if any), and final version used.
  4. Result summary with key IDs/names/states.
  5. If failed: exact failure reason and next fallback option.

8. Safety and Change Control

  • Default to read-only mode unless the user asks for mutations.
  • For destructive actions (delete/reset), require explicit confirmation in-task.
  • Never expose access tokens, client secrets, or sensitive headers in outputs.
  • Keep operations scoped to explicitly authorized tenants/subscriptions/resources.

9. Preferred Endpoint Templates

  • ARM base: https://management.azure.com{resourceId}?api-version=<VERSION>
  • Subscription resources: https://management.azure.com/subscriptions/<SUB_ID>/...?...
  • Graph beta: https://graph.microsoft.com/beta/...
  • Graph v1.0 fallback: https://graph.microsoft.com/v1.0/...

10. Practical Defaults

  • Use -o json and JMESPath filtering for concise evidence.
  • Preserve deterministic command ordering: discover -> validate scope -> execute -> verify.
  • When multiple APIs can satisfy a task, pick the newest endpoint family first, then fallback only as required.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.67%
按下载量换算73

Claude

31.5%
按下载量换算62

Cursor

17.02%
按下载量换算34

Gemini CLI

8.61%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/crtvrffnrt/skills --skill pentest-gemini-az 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills