lyrik

Analyze codebases for vulnerabilities and emit findings as JSON objects.

166|4|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/gebruder/wirken --skill lyrik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lyrik
Source: https://github.com/gebruder/wirken/tree/main/skills/lyrik
Command: npx skills add https://github.com/gebruder/wirken --skill lyrik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of security assessments for codebases, providing a comprehensive analysis and identifying potential vulnerabilities.

Core Features & Use Cases

  • Security Assessment: Run security assessments on codebases, identifying vulnerabilities across two framings (auth and injection).
  • Scoring and Reporting: Score identified vulnerabilities across four axes and aggregate findings into a report.
  • Recon and Emission Discipline: Follows strict rules for recon and emits findings exclusively through write_file tool calls.
  • Multi-run Aggregation: Aggregate findings across multiple runs to detect intrinsic drift in local models.

Quick Start

Run the lyrik skill on your codebase with the command: lyrik run

Frequently Asked Questions about lyrik

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

FAQPage Schema
How do I automate security assessments of my codebase?

You can automate codebase vulnerability detection by running the lyrik skill, which analyzes source code for security flaws and emits findings as structured JSON objects. It assesses risks across authentication and injection framings.

What types of vulnerabilities does codebase security analysis detect?

Codebase security analysis detects vulnerabilities by evaluating code across two primary framings: authentication and injection. Identified issues are then scored across four axes and aggregated into a comprehensive security report.

How do I aggregate findings from multiple security assessment runs?

You aggregate findings from multiple security assessment runs to detect intrinsic drift in local models. The skill compiles results across separate executions, consolidating scored vulnerabilities into a unified report.

Does automated vulnerability detection require specific tools or dependencies?

Automated vulnerability detection requires access to the target codebase and tools for vulnerability analysis, but operates with no external dependencies. It follows strict recon rules and emits findings exclusively through write_file tool calls.

What is the best way to report code vulnerabilities as JSON?

The best way to report code vulnerabilities as JSON is to use an automated security assessment that scores identified issues across four axes and emits them exclusively through write_file tool calls for structured output.