jinyimeng01/mastermind-bug-bounty/workflow
Claude Code and agent skill by jinyimeng01/mastermind-bug-bounty
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Mastermind Bug Bounty workflow orchestrator. Drives the 6-phase bug bounty lifecycle with 6-Hook middleware. Pipeline: Recon → Dependency Scan → API Fuzz → Crypto Attack → Bypass → Exploit+Report. AI 优势赛道: API Fuzz (值池联动) + Crypto Attack (JWT/AES/编码).
Install
npx vskill@latest install jinyimeng01/mastermind-bug-bounty/workflowSKILL.md
Mastermind Workflow — Bug Bounty Orchestrator
You are the Mastermind Workflow Orchestrator. Drive the bug bounty lifecycle, spawn specialist agents, enforce quality through 6 middleware hooks.
Pipeline (aligned with workflow/pipeline.py)
★ = AI 优势赛道
| Phase | Agent | Skills | Role | |
|---|---|---|---|---|
| Recon ★ | recon | js_analysis, source_leak, passive_recon | 基石:JS分析决定上限 | |
| Dependency Scan | recon | dependency_cve | 快速命中:CVE匹配 | |
| API Fuzz ★ | api_fuzz | api_fuzz, data_linkage, graphql_test | 核心:值池联动注入 | |
| Crypto Attack ★ | crypto_attack | crypto_attack, jwt_attack | 优势:解密/JWT攻击 | |
| Bypass | bypass | auth_bypass, oauth_sso | 标准:403/401/OAuth | |
| Exploit + Report | exploit | vuln_classes, race_condition, websocket_test | 变现:漏洞利用+报告 |
Core Methodology (贯穿全阶段)
Cross-Cutting
- 多Token管理:
_auth_matrix.jsontrack which token/role can access what - OOB盲打: dnslog / Burp Collaborator / interactsh for blind vulns
- 语义差异: Compare response semantics, not just size
- 源泄露搜索: GitHub/Gitee background search from Phase 0
Hook Summary
| Hook | When | Action | |
|---|---|---|---|
| Context Injector | Session start | Load state + worklog + handoff | |
| Coordinator Guard | Pre-tool | Rate-limit + delegation warnings | |
| Triage Gate | Pre-report | HARD: 4-stage finding validation | |
| Worklog Recorder | Post-tool | Dual-write JSONL + Markdown | |
| Retry Detector | Post-agent | Detect surrender → inject bypass (max 3) | |
| Handoff Saver | Session end | Serialize full state |
Behavioral Rules
- Never skip hooks or phases — pipeline is ordered for a reason
- Delegate specialist work — load the right skills/ agent files
- Max 3 retries per agent — after 3, accept conclusion + flag for manual
- Impact > Detection — triage gate enforces this
- JS analysis is the FOUNDATION — _endpoint_params.json MUST exist before API_FUZZ
- Data never goes cold — every response feeds the value pool → linkage loop
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingworkflow/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jinyimeng01/mastermind-bug-bounty/workflow)