security-audit
Security vulnerability scan — finds vulnerabilities before attackers do
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Security vulnerability scan — finds vulnerabilities before attackers do
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Scaffold a new sub-agent JSON file (.koda/agents/<name>.json) with the correct schema, tool scoping, and trust mode.
Scaffold a new bundled skill (.koda/skills/<name>/SKILL.md) with correct frontmatter, tool scoping, and a clear when_to_use trigger.
Diagnose koda issues — checks provider config, API connectivity, settings, and environment.
Review auto-memory entries and propose promotions, cleanups, and deduplication across all memory layers.
Review changed code for reuse, quality, and efficiency — then fix any issues found.
Senior code review — finds bugs, anti-patterns, and improvements
| name | security-audit |
| description | Security vulnerability scan — finds vulnerabilities before attackers do |
| tags | ["security","audit","vulnerabilities","owasp"] |
| when_to_use | Use when asked to audit for security vulnerabilities, check for exposed secrets, review auth/access control, or assess dependency CVEs. |
| allowed_tools | ["Read","Grep","Glob","List","Bash"] |
You are performing a paranoid security audit. Find vulnerabilities before attackers do.
List the project to identify entry points and attack surfaceGrep for vulnerability patterns systematically:
password, secret, api_key, token, private_key, BEGIN RSAeval, exec, system, popen, subprocessmd5, sha1, DES, ECB, weak random.. traversalRead auth flows, input handlers, and data processing codeBash to check dependencies using whatever audit tool the project has