Install in Claude Code
Copygit clone --depth 1 https://github.com/Ed1s0nZ/CyberStrikeAI /tmp/source-code-hunting && cp -r /tmp/source-code-hunting/skills/source-code-hunting ~/.claude/skills/source-code-huntingThen start a new Claude Code session; the skill loads automatically.
Definition
SKILL.md
## 源码狩猎
```
=== 源码狩猎 ===
.git泄露: git-dumper → git log -p --all(已删敏感文件) | .svn/.DS_Store/composer.lock
危险函数grep: exec/system/eval/unserialize/pickle.loads/render/curl_exec + 硬编码密钥(sk-/ghp_/BEGIN RSA)
JS混淆破解(RC4+base64字符串数组模式): 1)提取字符串数组(var a0G=[...]) 2)找解码函数(a0m(idx,key)→RC4解密+base64) 3)找rotation IIFE(目标偏移量) 4)Node.js重建解码器批量解码全部字符串→得到明文变量名/API路径/配置
UniApp特征: app-service.js(业务逻辑,常800KB+混淆) + zlsioh.dat(加密配置,native .so解密) + dcloud_uniplugins.json(插件清单)
静态扫描: semgrep --config=auto 快扫 / CodeQL建库写query (taint求解+变体分析方法论见 `zero-day-discovery`)
Secrets深挖: trufflehog/gitleaks 扫git全历史+docker镜像层+npm/PyPI tarball+前端bundle(--only-verified区分死活密钥)
框架Patch Diff: clone前后版本 diff → 修了什么=漏洞在哪 | 依赖链: composer.json/npm audit/pip-audit
供应链/CI: 依赖混淆(内部包名抢注公共registry) | GHA命令注入${{github.event.issue.title}} | self-hosted runner接管 | .npmrc/.pypirc凭据
```More from this repository
漏洞分诊专员Subagent
基于攻击面与证据线索进行漏洞候选筛选、优先级排序与“验证路径”设计(以证据为中心,不直接武器化),并要求主 Agent 提供完整目标与输入证据。
Plan-Execute 规划主代理Subagent
plan_execute 模式下的规划/重规划侧主代理:拆解目标、修订计划,由执行器调用 MCP 工具落地(不使用 Deep 的 task 子代理);计划中每步须含完整目标与范围,禁止让执行器凭猜测补全 URL/IP。
Supervisor 监督主代理Subagent
supervisor 模式下的协调者:通过 transfer 委派专家子代理,必要时亲自使用 MCP;完成目标时用 exit 结束(运行时会追加专家列表与 exit 说明);transfer 前必须提供完整目标与范围。
find-skillsSkill
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
api-security-testingSkill
API安全测试的专业技能和方法论
business-logic-testingSkill
业务逻辑漏洞测试的专业技能和方法论
cloud-security-auditSkill
云安全审计的专业技能和方法论
command-injection-testingSkill
命令注入漏洞测试的专业技能和方法论