I Built a Claude Code Skill That Refuses to Report Vulnerabilities It Can't Prove

Описание и применение

<p><strong>TL;DR:</strong> I previously built a <a href="https://dev.to/toshipon/i-built-a-claude-code-skill-that-runs-a-full-stack-security-audit-in-one-command-i6p">Claude Code skill that runs a full-stack security audit in one command</a> — a pattern library that tells the AI <em>where to look</em>. Running it in real engagements taught me that "where to look" and "how to conclude" are different skills. So I built a second skill, <a href="https://github.com/toshipon/claude-code-security-assessment-skill" rel="noopener noreferrer">security-assessment</a>, that governs how conclusions are rea

Задача

<p><strong>TL;DR:</strong> I previously built a <a href="https://dev.to/toshipon/i-built-a-claude-code-skill-that-runs-a-full-stack-security-audit-in-one-command-i6p">Claude Code skill that runs a full-stack security audit in one command</a> — a pattern library that tells the AI <em>where to look</em>. Running it in real engagements taught me that "where to look" and "how to conclude" are different skills. So I built a second skill, <a href="https://github.com/toshipon/claude-code-security-assessment-skill" rel="noopener noreferrer">security-assessment</a>, that governs how conclusions are rea

Результат

<p><strong>TL;DR:</strong> I previously built a <a href="https://dev.to/toshipon/i-built-a-claude-code-skill-that-runs-a-full-stack-security-audit-in-one-command-i6p">Claude Code skill that runs a full-stack security audit in one command</a> — a pattern library that tells the AI <em>where to look</em>. Running it in real engagements taught me that "where to look" and "how to conclude" are different skills. So I built a second skill, <a href="https://github.com/toshipon/claude-code-security-assessment-skill" rel="noopener noreferrer">security-assessment</a>, that governs how conclusions are rea

Доказательства

I Built a Claude Code Skill That Refuses to Report Vulnerabilities It Can't Prove

Источник