using-perseus
Use when starting a security conversation to understand the Perseus methodology
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 using-perseus技能说明
name: using-perseus description: Use when starting a security conversation to understand the Perseus methodology
Using Perseus
Overview
Perseus is a rigorous, automated security assessment framework for Claude Code. It transforms the AI into a structured penetration tester.
Core Principle: Methodological rigor over ad-hoc guessing. We do not "look around"; we execute specific phases.
The Workflow
The assessment follows a structured sequence. If subagents (Task, Agent, invoke_subagent) are available in your runtime, spawn specialists in parallel. If running in a single-agent CLI or session, execute each phase directly in the current session without failing.
Phase 1: Reconnaissance (/scan)
Goal: Map the attack surface.
- Action: Run
Skill: perseus-scan(or execute scan commands directly). - Output:
deliverables/code_analysis_deliverable.md(Target Knowledge Graph). - Stop Condition: Do not proceed until you know what to attack.
Phase 2: Vulnerability Analysis (Audit)
Goal: Prove potential vulnerability.
- Action: Run
Skill: perseus-audit(or execute audit commands directly). - Logic: Launch 5 parallel specialists (or 5 sequential passes: Injection, XSS, Auth, Authz, SSRF).
- Method: "Negative Analysis" (Source -> Flow -> Sink -> Defense -> Verdict).
- Output: Specialized reports in
deliverables/.
Phase 3: Exploitation & Verification (Exploit)
Goal: Verify impact (False Positive Filtering).
- Action: Run
Skill: perseus-exploit(or verify findings directly). - Safety: Use SAFE non-destructive proofs (code-level taint proofs, mock tests, harmless canaries).
- Output: Verified proofs in
deliverables/exploitation_report.md.
Phase 4: Reporting (/report)
Goal: Communicate risk and provide actionable fixes.
- Action: Run
Skill: perseus-report. - Output: Final
SECURITY_REPORT.mdwith executive summary, CVSS scoring, unified diff patches (git diff), and optional SARIF export.
Optional: Specialists (/specialist)
Goal: Run all deep-dive specialists (in parallel if subagents available, or sequentially).
- Action: Run
Skill: perseus-specialist(or/specialist).
Engagement Modes
Always select engagement mode before Phase 1. If user does not specify, default to PRODUCTION_SAFE.
| Mode | Intended Environment | Verification Style |
|---|---|---|
PRODUCTION_SAFE | Live production | Passive analysis + minimal non-disruptive verification |
STAGING_ACTIVE | Staging/pre-prod | Targeted active verification with throttling |
LAB_FULL | Isolated lab | Full dynamic verification for hard-to-reproduce findings |
LAB_RED_TEAM | Dedicated security lab | Adversarial chain simulation with strict legal scope |
Mode selection rule:
- If environment is unclear, assume production and use
PRODUCTION_SAFE. - If user requests aggressive testing, require explicit confirmation that target is staging/lab and authorized.
- Record chosen mode in deliverables so report consumers understand test depth.
Critical Rules
- No Hallucinations: Only report vulnerabilities you have verified via Audit or Exploit.
- Safe Mode: Never execute destructive commands (e.g.,
rm,DROP TABLE). - Evidence-Based: Every finding must cite a specific File:Line or HTTP Request/Response.
- Authorization Gate: Do not run active exploit validation on production without explicit approved test window.
- Stability First: Keep verification low-rate and stop immediately if service degradation appears.
- Lab Isolation for Red-Team Mode:
LAB_RED_TEAMonly on isolated test environment with non-production data.
How to Start
If the user asks for a security review, pentest, or audit, ALWAYS start with:
I will use the Perseus methodology to assess this codebase.
Starting Phase 1: Reconnaissance...
[Invoking /scan]