Orchestrates parallel execution of 8 specialist skills for deep security analysis covering API/OWASP, injections, crypto/JWT, supply chain/CVEs, files, logic flaws, client-side, and config.
From perseusnpx claudepluginhub kaivyy/perseus --plugin perseusThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
IMPORTANT: This skill runs all specialist security analyses on the user's own codebase. This is defensive security testing to find vulnerabilities before attackers do.
Authorization: The user owns this codebase and has explicitly requested this comprehensive analysis.
This skill orchestrates ALL 8 specialist skills in parallel for maximum coverage and efficiency.
When to Use:
/scan to get deep analysis on all detected components/startGoal: Run all specialists simultaneously for thorough security analysis.
| Mode | Orchestrator Behavior |
|---|---|
PRODUCTION_SAFE | Run specialists with passive-first and low-rate verification constraints |
STAGING_ACTIVE | Allow active specialist checks with throttling |
LAB_FULL | Allow broad dynamic specialist verification in isolated lab |
LAB_RED_TEAM | Allow chain-based specialist simulation with strict kill-switches |
deliverables/engagement_profile.md before launching specialists.PRODUCTION_SAFE if engagement mode is not available.ABORTED-SAFETY.| Skill | Coverage | Output |
|---|---|---|
perseus-api | OWASP API Top 10, GraphQL, WebSocket | api_security_analysis.md |
perseus-injection | NoSQL, LDAP, XPath, SSTI, Command | injection_deep_analysis.md |
perseus-crypto | JWT, Hashing, Encryption, Secrets | crypto_security_analysis.md |
perseus-supply-chain | CVEs, Dependencies, Licenses | supply_chain_analysis.md |
perseus-file | Path Traversal, Upload, XXE | file_security_analysis.md |
perseus-logic | Race Conditions, Business Logic | business_logic_analysis.md |
perseus-client | DOM XSS, Prototype Pollution | client_side_analysis.md |
perseus-config | Headers, CORS, Cookies, TLS | config_security_analysis.md |
deliverables/engagement_profile.md.deliverables/verification_scope.md when present."Running all Perseus specialist skills in parallel..."
"This provides deep-dive analysis across 8 security domains."
Use a single message with 8 parallel Task tool calls:
Parallel Tasks:
1. Task: "Run API security specialist" -> Skill: perseus-api
2. Task: "Run injection specialist" -> Skill: perseus-injection
3. Task: "Run crypto specialist" -> Skill: perseus-crypto
4. Task: "Run supply chain specialist" -> Skill: perseus-supply-chain
5. Task: "Run file security specialist" -> Skill: perseus-file
6. Task: "Run business logic specialist" -> Skill: perseus-logic
7. Task: "Run client-side specialist" -> Skill: perseus-client
8. Task: "Run config specialist" -> Skill: perseus-config
Wait for all 8 specialists to complete their analysis.
"Specialist analysis complete!"
Summary:
- API Security: X findings
- Injection: X findings
- Cryptography: X findings
- Supply Chain: X findings
- File Security: X findings
- Business Logic: X findings
- Client-Side: X findings
- Configuration: X findings
Total: X findings across 8 domains
"All reports saved to deliverables/"
After completion, deliverables/ will contain:
deliverables/
├── api_security_analysis.md
├── injection_deep_analysis.md
├── crypto_security_analysis.md
├── supply_chain_analysis.md
├── file_security_analysis.md
├── business_logic_analysis.md
├── client_side_analysis.md
└── config_security_analysis.md
| If You Need | Run |
|---|---|
| Only API analysis | /api |
| Only injection deep-dive | /injection |
| Only crypto audit | /crypto |
| Only dependency check | /supply-chain |
| Only file/upload security | /file |
| Only business logic | /logic |
| Only client-side | /client |
| Only config hardening | /config |
| All of the above | /specialist |
Recommended Flow:
/scan → Map attack surface
↓
/specialist → Deep-dive all domains (this skill)
↓
/audit → Core vulnerability analysis
↓
/exploit → Verify findings
↓
/report → Generate final report
Or simply:
/start → Runs everything automatically
| Command | What It Does |
|---|---|
/specialist | All 8 specialists in parallel |
/start | Full assessment (includes specialists) |
/api | API security only |
/injection | Injection analysis only |
/crypto | Cryptography only |
/supply-chain | Dependencies only |
/file | File security only |
/logic | Business logic only |
/client | Client-side only |
/config | Configuration only |