Token导航 LogoToken导航

Agent Skill · 研究检索

alibabacloud-dsc-audit(阿里巴巴云 DSC 审核)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

alibabacloud-dsc-audit 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 40,677。

总安装 1,261周安装 51GitHub Stars 80下载 396核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:alibabacloud-dsc-audit(阿里巴巴云 DSC 审核)
来源仓库:https://github.com/aliyun/alibabacloud-aiops-skills
仓库路径:skills/alibabacloud-dsc-audit
安装命令:
npx skills add https://github.com/aliyun/alibabacloud-aiops-skills --skill alibabacloud-dsc-audit
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/aliyun/alibabacloud-aiops-skills --skill alibabacloud-dsc-audit

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

alibabacloud-dsc-audit 用于查询和处理阿里云数据安全中心的风险事件。适用于安全审计、凭据风险检查与漏洞排查场景。alibabacloud-dsc-audit 属于研究检索类 Skill,可作为该场景下的辅助能力补充。支持查询风险规则与预处理审计事件,提供处置建议。

需安装指定 Python SDK 并配置阿里云凭证。不能将工具输出直接作为最终结论,需人工复核高风险项。

来源仓库内路径:skills/alibabacloud-dsc-audit

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/aliyun/alibabacloud-aiops-skills --skill aliba…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

alibabacloud-dsc-audit 怎么安装?

在终端执行 npx skills add https://github.com/aliyun/alibabacloud-aiops-skills --skill alibabacloud-ds…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

alibabacloud-dsc-audit 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

alibabacloud-dsc-audit 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

alibabacloud-dsc-audit 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

alibabacloud-dsc-audit 用的人多吗?

公开数据是累计安装 1,261 次,近一周安装 51 次,下载 396 次,GitHub 80 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

alibabacloud-dsc-audit 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
alibabacloud-dsc-audit

阿里巴巴云 DSC 审核 · 本页

1,26180接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Alibaba Cloud Data Security Center Risk Event Query and Handling

This skill uses Alibaba Cloud Python Common SDK (generic invocation) to query security risk events from the Data Security Center and handle them.

Architecture

User → Python Common SDK → Data Security Center (Sddp) API
                              ├── DescribeRiskRules (Query risk events)
                              └── PreHandleAuditRisk (Handle risk events)

Installation

pip3 install -r scripts/requirements.txt

Or install packages individually:

pip3 install alibabacloud_tea_openapi==0.4.3 alibabacloud_credentials==1.0.8 alibabacloud_tea_util==0.3.14 alibabacloud_openapi_util==0.2.4

[MUST] CLI User-Agent — Every aliyun CLI command invocation must include: --user-agent AlibabaCloud-Agent-Skills/alibabacloud-dsc-audit

Pre-check: Aliyun CLI >= 3.3.3 required Run aliyun version to verify >= 3.3.3. If not installed or version too low, run curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash to update, or see references/cli-installation-guide.md for installation instructions.
Pre-check: Aliyun CLI plugin update required [MUST] run aliyun configure set --auto-plugin-install true to enable automatic plugin installation. [MUST] run aliyun plugin update to ensure that any existing plugins are always up-to-date.

At the start of the Core Workflow (before any CLI invocation): [MUST] Enable AI-Mode — AI-mode is required for Agent Skill execution. Run the following commands before any CLI invocation:

aliyun configure ai-mode enable
aliyun configure ai-mode set-user-agent --user-agent "AlibabaCloud-Agent-Skills/alibabacloud-dsc-audit"

[MUST] Disable AI-Mode at EVERY exit point — Before delivering the final response for ANY reason, always disable AI-mode first. This applies to ALL exit paths: workflow success, workflow failure, error/exception, user cancellation, session end, or any other scenario where no further CLI commands will be executed. AI-mode is only used for Agent Skill invocation scenarios and MUST NOT remain enabled after the skill stops running.

aliyun configure ai-mode disable

Authentication

Pre-check: Alibaba Cloud Credentials Required Security Rules: - NEVER read, echo, or print AK/SK values (e.g., echo $ALIBABA_CLOUD_ACCESS_KEY_ID is FORBIDDEN) - NEVER ask the user to input AK/SK directly in the conversation or command line - NEVER use aliyun configure set with literal credential values - ONLY use aliyun configure list to check credential status ``bash aliyun configure list ` Check the output for a valid profile (AK, STS, or OAuth identity). **If no valid profile exists, STOP here.** 1. Obtain credentials from [Alibaba Cloud Console](https://ram.console.aliyun.com/manage/ak) 2. Configure credentials **outside of this session** (via aliyun configure in terminal or environment variables in shell profile) 3. Return and re-run after aliyun configure list` shows a valid profile

RAM Permissions

Before using this skill, ensure the current user has the required RAM permissions. For detailed permission lists and policy configurations, refer to references/ram-policies.md

Parameter Confirmation

IMPORTANT: Parameter Confirmation — Before executing any command or API call, ALL user-customizable parameters (e.g., RegionId, instance names, CIDR blocks, passwords, domain names, resource specifications, etc.) MUST be confirmed with the user. Do NOT assume or use default values without explicit user approval.
ParameterRequired/OptionalDescriptionDefault
CurrentPageOptionalCurrent page number1
PageSizeOptionalRecords per page10
HandleStatusOptionalProcessing status, PROCESSED means handled, UNPROCESSED means not handledUNPROCESSED
RiskIdRequired for handlingRisk event ID-
HandleDetailRequired for handlingHandling details description-

Core Workflow

Step 1: Query Unprocessed Security Risk Events

Use the scripts/query_risk.py script to query unprocessed security risk events. This is a paginated API that returns the first 20 records by default.

python3 scripts/query_risk.py

Example output:

Found 31 unprocessed security risk events
================================================================================
Risk ID: 75110196
Rule Name: jiangyu_test_mysqldump
Risk Level: High Risk
Product Type: RDS
Alert Count: 20
Asset Count: 2
Rule Category: Database Dump Attack
--------------------------------------------------------------------------------

Query Result Field Descriptions

The query results return the following key fields. Risk Event ID (RiskId) is a required parameter for handling:

FieldDescription
RiskIdRisk event ID, required for handling
RuleNameRule name
WarnLevelNameRisk level (High Risk/Medium Risk/Low Risk)
ProductCodeProduct type (RDS/OSS, etc.)
AlarmCountAlert count
InstanceCountNumber of affected assets
FirstAlarmTimeFirst discovery time
LastAlarmTimeLast discovery time

Step 2: Handle Security Risk Events

Use the scripts/handle_risk.py script to handle specified risk events.

python3 scripts/handle_risk.py <RiskID> <HandleDetail>

Example:

python3 scripts/handle_risk.py 75110196 "Confirmed as false positive, closing this alert"

Example output:

Handling risk event...
Risk ID: 75110196
Handle Detail: Confirmed as false positive, closing this alert
--------------------------------------------------
✅ Handling successful!
RequestId: C34D813F-A234-5D66-842D-504D84D5C680

Handling Parameter Descriptions

ParameterDescription
RiskIdRisk event ID, obtained from DescribeRiskRules API
HandleTypeHandling type, fixed as Manual (manual handling)
HandleMethodHandling method, fixed as 0
HandleDetailHandling details, requires user to input specific handling description

Success Verification

Verify Query Operation

  1. After executing the query code, check if the returned statusCode is 200
  2. Check if the returned body contains the Items list
  3. Verify that TotalCount matches the actual number of returned records

Verify Handling Operation

  1. After executing the handling code, check if the returned statusCode is 200
  2. Call DescribeRiskRules again to query the RiskId and confirm the status has changed

Cleanup

This skill is primarily used for query and handling operations, does not involve resource creation, and requires no cleanup.

API and Command Reference

ProductAPI ActionScriptDescription
SddpDescribeRiskRulesscripts/query_risk.pyQuery security risk events
SddpPreHandleAuditRiskscripts/handle_risk.pyHandle security risk events

Script Usage

ScriptUsageDescription
query_risk.pypython3 scripts/query_risk.pyExecute directly, no parameters required
handle_risk.pypython3 scripts/handle_risk.py <RiskID> <HandleDetail>Requires Risk ID and handling description

For detailed API information, refer to references/related-apis.md

Best Practices

  1. Paginated Query: When using paginated APIs, increment the CurrentPage parameter until all records are retrieved
  2. Record RiskId: The RiskId in query results is a required parameter for handling operations, make sure to record it
  3. Handle Description: Provide a clear HandleDetail description when handling for subsequent auditing
  4. Error Handling: Implement retry mechanisms for temporary errors like Throttling
  5. Credential Security: Use CredentialClient to manage credentials, do not hardcode AK/SK

Reference Links

Reference DocumentDescription
references/related-apis.mdAPI detailed documentation
references/ram-policies.mdRAM permission configuration
references/cli-installation-guide.mdCLI installation guide
references/acceptance-criteria.mdAcceptance criteria
Generic Invocation DocumentationAlibaba Cloud Python SDK generic invocation documentation

Important Notes

Warning: This skill only uses the Data Security Center's DescribeRiskRules and PreHandleAuditRisk APIs. If these two APIs cannot be found, report an error. Do NOT call other OpenAPIs without authorization. Do not use Alibaba Cloud CLI tools to call APIs.

平台分布

Claude

32.49%
按下载量换算129

Codex

31.77%
按下载量换算126

Cursor

17.25%
按下载量换算68

Gemini CLI

8.92%
按下载量换算35

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills