perseus-start
Use when you want to run a full, automated penetration test from start to finish (Scan -> Audit -> Exploit -> Report)
kaivyy · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add kaivyy/perseus --skill perseus-start技能说明
name: perseus-start description: Use when you want to run a full, automated penetration test from start to finish (Scan -> Audit -> Exploit -> Report)
Perseus Start (Automated Security Assessment)
Context & Authorization
IMPORTANT: This skill orchestrates a complete security assessment on the user's own codebase. This is defensive security testing - the user is proactively finding vulnerabilities in their own code before attackers do.
Authorization: The user has explicitly invoked this assessment on their own codebase in their own development environment. This is equivalent to running a comprehensive test suite, static analyzer, or security audit tool.
This is NOT an attack on external systems. All analysis is performed on local files the user owns and controls.
Overview
This master skill orchestrates the entire Perseus security assessment lifecycle with smart auto-detection of languages, frameworks, and technologies.
Goal: Zero-touch automated security assessment with professional-grade output.
Agent Execution Strategy (Dual-Mode)
When orchestrating Perseus, adapt to the runtime capabilities:
- Mode A — Subagents Available (Multi-Agent/Parallel):
If subagent tools (e.g.
Task,Agent,invoke_subagent) are available, launch phase agents and specialist deep-dives in parallel. - Mode B — Direct Execution (Single-Agent Fallback — UNIVERSAL):
If no subagent tool exists in your runtime, DO NOT attempt to call non-existent subagent tools. Execute each phase directly in sequence:
Phase -1 (Setup)➔Phase 0 (Detect)➔Phase 1 (Scan)➔Phase 2 (Audit)➔Phase 2.5 (Specialists)➔Phase 3 (Exploit Verify)➔Phase 4 (Report). Ensuremkdir -p deliverablesis run first and write all files directly intodeliverables/.
Engagement Mode (Required)
Before running phases, select one mode:
| Mode | Environment | Behavior |
|---|---|---|
PRODUCTION_SAFE | Live production | Passive-first analysis and minimal safe verification only |
STAGING_ACTIVE | Staging/pre-production | Active safe payload testing with request throttling |
LAB_FULL | Isolated lab | Full dynamic verification and payload mutation |
LAB_RED_TEAM | Dedicated lab environment | Multi-step adversarial simulation with kill-switches |
Default mode is PRODUCTION_SAFE unless user explicitly confirms staging/lab authorization.
Smart Auto-Detection
Before starting the assessment, Perseus automatically detects:
Language Detection
| Files | Language |
|---|---|
| package.json, *.ts, *.js | JavaScript/TypeScript |
| go.mod, *.go | Go |
| composer.json, *.php | PHP |
| requirements.txt, *.py | Python |
| Cargo.toml, *.rs | Rust |
| pom.xml, *.java | Java |
| Gemfile, *.rb | Ruby |
| *.csproj, *.cs | C# |
Framework Detection
| Files/Patterns | Framework |
|---|---|
| next.config.*, app/ directory | Next.js |
| nuxt.config.* | Nuxt.js |
| angular.json | Angular |
| vite.config., svelte.config. | Vite/Svelte |
| gin import, echo import | Go (Gin/Echo) |
| artisan, laravel | PHP (Laravel) |
| manage.py, django | Python (Django) |
| fastapi import | Python (FastAPI) |
| actix-web, axum in Cargo.toml | Rust (Actix/Axum) |
| spring-boot | Java (Spring) |
| rails | Ruby on Rails |
Infrastructure Detection
| Files | Technology |
|---|---|
| Dockerfile, docker-compose.yml | Docker |
| .github/workflows/*.yml | GitHub Actions |
| .gitlab-ci.yml | GitLab CI |
| *.tf | Terraform |
| k8s/, kubernetes/, *.yaml with apiVersion | Kubernetes |
| serverless.yml | Serverless |
| vercel.json | Vercel |
API Detection
| Patterns | Type |
|---|---|
| /graphql, schema.graphql, *.gql | GraphQL |
| WebSocket, ws://, wss:// | WebSocket |
| *.proto, grpc | gRPC |
| openapi, swagger | REST/OpenAPI |
AI/LLM Detection
| Patterns | Technology |
|---|---|
| openai, anthropic, langchain | LLM Integration |
| vector store, embeddings | RAG System |
| prompt, completion | AI Features |
Complete Capability Matrix
Core Phases (Always Run)
| Phase | Skill | Purpose |
|---|---|---|
| 1 | scan | Map architecture, entry points, attack surface |
| 2 | audit | Analyze all vulnerability classes |
| 3 | exploit | Verify findings with safe PoCs |
| 4 | report | Generate executive security report |
Specialist Deep-Dives (Run When Detected)
| Skill | Trigger Condition | Extended Coverage |
|---|---|---|
| api | REST/GraphQL/WebSocket/gRPC | +OAuth, Cache, multi-lang |
| injection | NoSQL/Templates/Commands | +Log4j, SSTI, multi-lang |
| crypto | JWT/Encryption/Hashing | +multi-lang patterns |
| supply-chain | Package manifests | +multi-lang, typosquatting |
| file | File uploads/operations | +Zip Slip, XXE, multi-lang |
| logic | Payment/Auth/AI flows | +AI prompt injection |
| client | React/Vue/Angular/SSR | +Server Components, Actions |
| config | Always | +Docker, CI/CD, Cloud, K8s |
Execution Flow
Phase -1: Engagement Setup
Action: Determine mode and boundaries
1. Detect runtime context (production/staging/lab)
2. Ask for explicit authorization scope if context is unclear
3. Set mode: PRODUCTION_SAFE, STAGING_ACTIVE, LAB_FULL, or LAB_RED_TEAM
4. Create deliverables/engagement_profile.md with:
- mode
- in-scope targets
- excluded systems
- request-rate limits
- approved test window
- kill-switch thresholds (error rate, latency, saturation)
Announce: "Engagement mode set to: [MODE]"
Phase 0: Auto-Detection
Action: Detect project technologies
# Initialize directories and detect technology manifests
mkdir -p deliverables outputs/schemas
ls -d package.json go.mod composer.json requirements.txt pyproject.toml Cargo.toml pom.xml build.gradle Gemfile *.csproj Dockerfile 2>/dev/null || true
1. Scan for package manifests:
阅读完整来源 ↗