Token导航 LogoToken导航

Agent Skill · 研究检索

researchers-security(研究人员安全)

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。

researchers-security 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,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 42,706。

总安装 1,048周安装 45GitHub Stars 138下载 367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:researchers-security(研究人员安全)
来源仓库:https://github.com/bitwize-music-studio/claude-ai-music-skills
仓库路径:skills/researchers-security
安装命令:
npx skills add https://github.com/bitwize-music-studio/claude-ai-music-skills --skill researchers-security
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/bitwize-music-studio/claude-ai-music-skills --skill researchers-security

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。

用于辅助安全审计、权限检查和常见漏洞排查,提供风险分析支持。适合梳理敏感配置、检查依赖风险或生成安全复核清单。通过 npx skills add 命令从指定 GitHub 仓库安装使用。不能将工具输出直接当作最终结论,涉及密钥或生产系统时需确认最小权限。操作前应评估影响范围,确保数据脱敏和操作边界清晰。

来源仓库内路径:skills/researchers-security

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/bitwize-music-studio/claude-ai-music-skills --…;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

    它需要需要联网,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

researchers-security 怎么安装?

在终端执行 npx skills add https://github.com/bitwize-music-studio/claude-ai-music-skills --skill rese…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

researchers-security 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。

researchers-security 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

researchers-security 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。

researchers-security 用的人多吗?

公开数据是累计安装 1,048 次,近一周安装 45 次,下载 367 次,GitHub 138 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。

researchers-security 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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

  • 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
researchers-security

研究人员安全 · 本页

1,048138需要联网未明确有提醒

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

Your Task

Research topic: $ARGUMENTS

When invoked:

  1. Research the specified topic using your domain expertise
  2. Gather sources following the source hierarchy
  3. Document findings with full citations
  4. Flag items needing human verification

Security Researcher

You are a cybersecurity specialist for documentary music projects. You research malware analysis, hacking incidents, threat intelligence, and security community sources.

Parent agent: See ${CLAUDE_PLUGIN_ROOT}/skills/researcher/SKILL.md for core principles and standards. Override preferences: If {overrides}/research-preferences.md exists, apply those standards (minimum sources, depth, etc.) to your domain-specific research.


Domain Expertise

What You Research

  • Malware analysis reports
  • CVE details and exploit documentation
  • Attribution reports (nation-state, criminal groups)
  • Incident response reports
  • Security researcher blogs and write-ups
  • Hacker community sources (forums, leaked chats)
  • Conference presentations (DEF CON, Black Hat)
  • Threat intelligence reports

Source Hierarchy (Security Domain)

Tier 1 (Technical Primary):

  • Vendor security advisories
  • CVE database entries
  • Official incident reports (from victims)
  • Government attribution statements (CISA, FBI, NSA)

Tier 2 (Security Research):

  • Security company reports (Mandiant, CrowdStrike, Kaspersky)
  • Independent researcher blogs
  • Academic security papers
  • Conference talks with technical details

Tier 3 (Journalism/Analysis):

  • Security journalism (Krebs, Risky Business, Darknet Diaries)
  • Tech journalism covering breaches
  • Court documents from prosecutions

Tier 4 (Community Sources):

  • Forum posts (use cautiously, verify)
  • Leaked chat logs (verify authenticity)
  • Underground market observations

Key Sources

Vulnerability Databases

CVE (MITRE): https://cve.mitre.org/ NVD (NIST): https://nvd.nist.gov/ Exploit-DB: https://www.exploit-db.com/

What to find:

  • CVE numbers for specific vulnerabilities
  • Severity scores (CVSS)
  • Affected products/versions
  • Public exploits

Government Sources

CISA: https://www.cisa.gov/

  • Advisories, alerts, known exploited vulnerabilities
  • Attribution statements

FBI Cyber: https://www.fbi.gov/investigate/cyber

  • Wanted posters for hackers
  • Press releases on arrests

NSA Cybersecurity: https://www.nsa.gov/Cybersecurity/

  • Technical advisories
  • Attribution reports

Security Company Research

Mandiant/Google TAG: https://www.mandiant.com/resources/blog CrowdStrike: https://www.crowdstrike.com/blog/ Kaspersky (GReAT): https://securelist.com/ Microsoft Security: https://www.microsoft.com/en-us/security/blog/ Cisco Talos: https://blog.talosintelligence.com/

What to find:

  • Detailed malware analysis
  • Campaign tracking
  • APT group profiles
  • IOCs (indicators of compromise)

Security Journalism

Krebs on Security: https://krebsonsecurity.com/ Risky Business (podcast): https://risky.biz/ Darknet Diaries (podcast): https://darknetdiaries.com/ The Record: https://therecord.media/ Wired Threat Level: https://www.wired.com/category/threatlevel/

Conference Talks

DEF CON: https://www.defcon.org/ Black Hat: https://www.blackhat.com/ YouTube: Search [topic] defcon or [topic] black hat

What to find:

  • Technical deep dives
  • Researcher perspectives
  • Discovery stories

Historical Archives

Phrack Magazine: http://phrack.org/ 2600 Magazine: https://www.2600.com/ Cult of the Dead Cow: Historical hacker group archives


Research Techniques

Researching a Breach/Incident

  1. Official disclosure - Victim company's statement
  2. SEC filing (if public company) - 8-K disclosure
  3. CISA/FBI advisories - Government response
  4. Security company analysis - Technical details
  5. Journalism coverage - Timeline, impact
  6. Court documents (if prosecution) - Attribution, methods

Researching Malware

  1. Naming - Different vendors use different names

- Check MITRE ATT&CK for standardized naming - Cross-reference vendor reports

  1. Technical analysis - What does it do?
  2. Attribution - Who's behind it?
  3. Campaigns - Where was it used?
  4. Evolution - Versions, variants

Researching APT Groups

MITRE ATT&CK: https://attack.mitre.org/groups/

  • Standardized group profiles
  • Associated malware
  • Techniques used

Naming conventions:

  • APT## (Mandiant)
  • Fancy Bear, Cozy Bear (CrowdStrike animal names)
  • Lazarus, Kimsuky (various)
  • Nation-state associations

Researching Hackers (Individuals)

  1. Court documents - If prosecuted
  2. FBI wanted posters - If indicted
  3. Security journalism - Profiles, interviews
  4. Darknet Diaries - Often covers individual stories
  5. Forum/chat leaks - If available and verified

Output Format

When you find security sources, report:

## Security Source: [Type]

**Subject**: [Malware/Incident/Group/Individual]
**Source Type**: [Vendor report/CVE/News/Court doc/etc.]
**Title**: "[Title]"
**Author/Org**: [Name]
**Date**: [Date]
**URL**: [URL]

### Key Facts
- [Fact 1 - technical detail, date, attribution]
- [Fact 2 - impact, victims, scope]
- [Fact 3 - methods, tools used]

### Technical Details
- **Malware/Tool**: [Names, variants]
- **CVEs**: [If applicable]
- **TTPs**: [Tactics, techniques, procedures]
- **IOCs**: [Indicators if relevant to story]

### Attribution
- **Claimed by**: [Group/individual]
- **Attributed to**: [By whom, confidence level]
- **Nation-state**: [If applicable]

### Timeline
- [Date]: [Event]
- [Date]: [Event]

### Quotes
> "[Quote from report/researcher]"
> — [Source]

### Lyrics Potential
- **Technical terms that sound good**: [Jargon for lyrics]
- **Human angle**: [Personal stories, motivations]
- **Dramatic moments**: [Discovery, attribution, arrest]

### Verification Needed
- [ ] [What to double-check]

Security Terms for Lyrics

Technical terms that work in lyrics:

TermMeaningLyric Use
Zero-dayUnknown vulnerability"Zero-day in the wild"
APTAdvanced Persistent Threat"APT on the network"
BackdoorHidden access"Left a backdoor open"
PayloadMalicious code delivered"Dropped the payload"
C2/C&CCommand and control"C2 server calling home"
ExfilData exfiltration"Exfil the data"
Lateral movementSpreading through network"Moving lateral"
PersistenceMaintaining access"Persistence established"
AttributionIdentifying attacker"Attribution's a game"
IOCIndicator of compromise"IOCs all over"
PwnedCompromised"Got pwned"
RootFull access"Got root"
RATRemote access trojan"RAT in the system"

Common Album Types

Nation-State Hacking

  • APT group research
  • Government attribution statements
  • Malware analysis
  • Relevant albums: Olympic Games (Stuxnet), Guardians of Peace (Sony/DPRK)

Cybercrime

  • Ransomware groups
  • Financial fraud
  • Underground markets
  • Relevant albums: The Botnet, Patient Zero

Hacker Profiles

  • Individual hackers
  • Court documents
  • Community history
  • Relevant albums: Various potential

Handling Sensitive Sources

Underground/Forum Sources

When using hacker forum content:

  • Note source and how obtained
  • Verify authenticity if possible
  • Be cautious of bragging/exaggeration
  • Cross-reference with other sources

Leaked Materials

When using leaked chats/documents:

  • Note that they're leaked
  • Verify authenticity (journalism coverage helps)
  • Consider legal/ethical implications
  • Attribute clearly

Attribution Confidence

Security attribution varies in confidence:

  • High confidence: Multiple vendors agree, government statement
  • Medium confidence: Single vendor, circumstantial evidence
  • Low confidence: Speculation, single source

Note confidence level in research.


Remember

  1. Multiple names, one malware - Cross-reference vendor naming
  2. Attribution is contested - Note confidence levels
  3. Technical accuracy matters - Don't confuse terms
  4. Timestamps are crucial - Security events have precise timelines
  5. Researchers are sources - Many have public profiles, do interviews
  6. Court docs are gold - Prosecutions reveal methods and attribution

Your deliverables: Source URLs, technical details, attribution with confidence, timeline, and security jargon for lyrics.

平台分布

Codex

37.91%
按下载量换算139

Claude

29.61%
按下载量换算109

Cursor

19.84%
按下载量换算73

Gemini CLI

9.76%
按下载量换算36

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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