SRC Hunter Security Research Agent Skill
Facilitates structured vulnerability discovery and security research workflows for authorized penetration testing and bug bounty programs.
- Context cost
- 912k tokensestimated from the bundle; more than a 200k window holds
- Bundle
- 91 files · 3647.8 kBtext throughout, nothing executable
- Licence
- MITthe author’s own terms
- Last change
- —no release on file
- Servers it uses
- Noneruns standalone
What it does
实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含：5 阶段方法论（intake → recon → enum → hunt → report）、19 个攻击类 playbook（SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS）、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical 已披露案例、77,000+ WooYun 案例统计、国产 OA / 中间件指纹库、银行 / 电信行业垂直 playbook。当用户提到 "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" 或问"如何挖某个目标 / 怎么测某个 API / 如何绕过 WAF" 时触发。
Installed, it changes the agent in these ways.
What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.
And these are the jobs people reach for it for.
The skill itself
A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.
Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.
What it costs in context
Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.
912k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.
A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.
Before and after
The same question, put to the same model twice: once as it comes, and once with these instructions loaded.
No worked example has been published for this skill yet.
The procedure it runs
The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.
These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.
Servers it uses
None. This skill calls no MCP servers at all.
Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.
Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.
This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.
What it will not do
Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.
What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.
What is in the bundle
91 files, 3647.8 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in. 2 files of its source are not in the download — listed after these, with why.
- SKILL.md12.0 kB
- LICENSE1.1 kB
- README.en.md6.3 kB
- README.md6.4 kB
- .claude-plugin/marketplace.json1.1 kB
- references/dictionaries/00-index.md2.3 kB
- references/dictionaries/chinese-srcfingerprints.md14.9 kB
- references/dictionaries/default-credentials-cn.md10.1 kB
- references/industry/00-index.md2.8 kB
- references/industry/banking-finance.md14.9 kB
- references/industry/telecom-isp.md11.8 kB
- references/methodology/00-index.md2.9 kB
- references/methodology/01-attack-priority.md6.6 kB
- references/methodology/02-bypass-toolkit.md11.6 kB
- references/methodology/03-evidence-discipline.md7.5 kB
- references/methodology/04-control-gap-hunting.md9.3 kB
- references/methodology/05-srctimebox-priority.md7.9 kB
- references/payloader/index.md5.2 kB
- references/payloader/waf-bypass.md173.7 kB
- references/playbooks/00-index.md2.7 kB
- references/playbooks/api-rest.md46.2 kB
- references/playbooks/arbitrary-x-authz.md20.6 kB
- references/playbooks/dos.md27.7 kB
- references/playbooks/file-upload.md45.4 kB
- references/playbooks/graphql.md5.6 kB
- references/playbooks/http-smuggling.md21.6 kB
- references/playbooks/info-disclosure.md16.3 kB
- references/playbooks/intranet-postexp.md110.1 kB
- references/playbooks/llm-prompt-injection.md56.5 kB
- references/playbooks/logic-flaws.md51.5 kB
- references/playbooks/mobile.md13.9 kB
- references/playbooks/oauth-saml-jwt.md79.1 kB
- references/playbooks/path-traversal.md32.7 kB
- references/playbooks/race-conditions.md7.1 kB
- references/playbooks/rce.md123.4 kB
- references/playbooks/sqli.md45.5 kB
- references/playbooks/ssrf-cache-host.md63.0 kB
- references/playbooks/unauth-access.md14.3 kB
- references/playbooks/xss.md30.7 kB
- references/templates/report-submission.md9.8 kB
- references/tools/mcp-jshook.md16.1 kB
- references/payloader/raw/navigation.json156.1 kB
- references/payloader/raw/tools.json173.6 kB
- references/payloader/raw/web.json1147.9 kB
- references/payloader/tools/web渗透.md12.9 kB
- references/payloader/tools/windows渗透.md2.1 kB
- references/payloader/tools/信息收集.md15.5 kB
- references/payloader/tools/内网渗透.md15.3 kB
- references/payloader/tools/凭证窃取.md2.8 kB
- references/payloader/tools/域渗透.md0.9 kB
- references/payloader/tools/密码攻击.md9.4 kB
- references/payloader/tools/权限提升.md2.1 kB
- references/payloader/tools/漏洞利用.md9.6 kB
- references/payloader/tools/系统命令.md7.9 kB
- references/payloader/tools/红队工具.md0.8 kB
- references/payloader/tools/编码解码.md4.7 kB
- references/payloader/tools/隧道代理.md1.1 kB
- references/payloader/by-category/intranet/adcs攻击.md6.3 kB
- references/payloader/by-category/intranet/exchange攻击.md5.7 kB
- references/payloader/by-category/intranet/sharepoint攻击.md2.5 kB
- references/payloader/by-category/intranet/信息收集.md22.0 kB
- references/payloader/by-category/intranet/免杀与规避.md18.7 kB
- references/payloader/by-category/intranet/凭证窃取.md35.0 kB
- references/payloader/by-category/intranet/域渗透攻击.md18.4 kB
- references/payloader/by-category/intranet/权限提升.md21.6 kB
- references/payloader/by-category/intranet/权限维持.md14.0 kB
- references/payloader/by-category/intranet/横向移动.md21.3 kB
- references/payloader/by-category/intranet/隧道代理.md12.8 kB
- references/payloader/by-category/web/ai安全.md32.1 kB
- references/payloader/by-category/web/api安全.md46.1 kB
- references/payloader/by-category/web/csrf跨站请求伪造.md24.2 kB
- references/payloader/by-category/web/jwt安全.md20.0 kB
- references/payloader/by-category/web/lfi-rfi文件包含.md35.9 kB
- references/payloader/by-category/web/rce远程代码执行.md38.6 kB
- references/payloader/by-category/web/sql-nosql注入.md63.1 kB
- references/payloader/by-category/web/ssrf服务端请求伪造.md37.7 kB
- references/payloader/by-category/web/ssti模板注入.md32.1 kB
- references/payloader/by-category/web/websocket安全.md20.6 kB
- references/payloader/by-category/web/xss跨站脚本.md44.5 kB
- references/payloader/by-category/web/xxe实体注入.md24.9 kB
- references/payloader/by-category/web/业务逻辑漏洞.md25.4 kB
- references/payloader/by-category/web/云安全漏洞.md26.9 kB
- references/payloader/by-category/web/供应链攻击.md17.8 kB
- references/payloader/by-category/web/原型链污染.md19.1 kB
- references/payloader/by-category/web/开放重定向.md14.0 kB
- references/payloader/by-category/web/文件漏洞.md48.0 kB
- references/payloader/by-category/web/框架漏洞.md68.8 kB
- references/payloader/by-category/web/点击劫持.md14.0 kB
- references/payloader/by-category/web/缓存与cdn安全.md17.3 kB
- references/payloader/by-category/web/认证漏洞.md65.1 kB
- references/payloader/by-category/web/请求走私.md22.4 kB
Not in the download
Not carried is a type a skill download does not hold. Take them from its source.
- .gitignorenot carried
- references/.gitkeepnot carried
No dependencies and nothing executable: a skill is text the agent reads, so the download is 91 files — not the whole of its source: 2 files are left out. They are listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.
Install
Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.
# SRC Hunter Security Research · 912k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/src-hunter-security-research/bundle.tar.gz &&
tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/src-hunter-security-research" ] &&
{ [ ! -e .claude/skills/src-hunter-security-research ] || { mv .claude/skills/src-hunter-security-research "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
mv "$t/src-hunter-security-research" .claude/skills/ && echo "Installed .claude/skills/src-hunter-security-research"npx mcprush@latest skill add zhaoxuya520/src-hunter-security-researchWindows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/src-hunter-security-research/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/src-hunter-security-research/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/src-hunter-security-research" ] && { [ ! -e ~/.claude/skills/src-hunter-security-research ] || { mv ~/.claude/skills/src-hunter-security-research "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/src-hunter-security-research" ~/.claude/skills/ && echo "Installed ~/.claude/skills/src-hunter-security-research" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/src-hunter-security-research/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as src-hunter in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, src-hunter-security-research. Not in this download: 2 files of its source (the full list, and why). Take them from its source.
Which clients pick it up on their own
A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.
Versions
Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.
Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.
Reviews
Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.
A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.
Sign inAnybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.