referee

Verify bug reports and assign CVSS scores with proof-of-concept examples.

479|56|Updated Mar 7, 2026
One-click install
npx skills add https://github.com/codexstar69/bug-hunter --skill referee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: referee
Source: https://github.com/codexstar69/bug-hunter/tree/main/skills/referee
Command: npx skills add https://github.com/codexstar69/bug-hunter --skill referee

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill acts as the final, impartial judge in the Bug Hunter pipeline, resolving disputes between Hunters and Skeptics by independently verifying bug reports and assigning authoritative verdicts with CVSS scoring.

Core Features & Use Cases

  • Independent Verification: Re-reads code and traces execution paths to confirm or deny bug reports.
  • Severity Calibration: Assigns accurate CVSS scores and severity levels (Critical, High, Medium, Low) to confirmed security vulnerabilities.
  • Proof-of-Concept Generation: Creates minimal, benign Proof-of-Concept examples for critical and high-severity security findings.
  • Use Case: After Hunters flag a potential SQL injection and Skeptics challenge it, the Referee independently analyzes the code, confirms the vulnerability, assigns a CVSS score, and generates a PoC to demonstrate the exploit.

Quick Start

Use the referee skill to evaluate the provided hunter and skeptic reports for bug ID BUG-1.

Frequently Asked Questions about referee

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I independently verify disputed security vulnerabilities during code review?

To independently verify disputed security vulnerabilities, an impartial arbiter re-reads the source code and traces execution paths to confirm or deny bug reports, assigning authoritative verdicts based on concrete code evidence.

How does CVSS scoring work for confirmed security findings?

CVSS scoring for confirmed security findings works by calibrating the vulnerability's severity level—Critical, High, Medium, or Low—after independently tracing the execution path and verifying the exploitability of the code.

Can I generate a proof of concept for a high severity bug report?

Yes, you can generate a proof of concept for high severity bug reports. After confirming a vulnerability and assigning a CVSS score, the arbiter creates minimal, benign PoC examples to demonstrate the exploit.

What is the best way to resolve disputes between bug hunters and skeptics?

The best way to resolve disputes between bug hunters and skeptics is through an independent verification process that re-reads code, evaluates evidence quality, and delivers an impartial, authoritative verdict on the flagged vulnerability.

Do I need to trace execution paths manually for security analysis?

No, you do not need to trace execution paths manually for security analysis. An automated arbiter can independently re-read the code, verify the bug report, and generate proof of concept examples without manual execution tracing.

When should I use an impartial arbiter for bug hunting?

You should use an impartial arbiter for bug hunting when a hunter flags a potential vulnerability and a skeptic challenges it, requiring independent code verification, severity calibration, and proof of concept generation.