AGENT SKILL

skill-stocktake

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

License 许可
Apache-2.0
最近更新
2026-11-08
Stars
★ 0
Forks
0

01 前言 Front Matter

name
fe-security
description
Audit frontend code for security vulnerabilities: XSS, auth token storage, API key exposure, and client-side data safety.
allowed-tools
Read, Glob, Grep, Task
argument-hint
[file-or-directory-path]
user-invocable
true

02 资源文件 3

03 SKILL.md 正文

Security Audit

Audit frontend React/TypeScript code for security vulnerabilities across XSS, authentication, secrets exposure, and client-side data safety.

Instructions

Step 0: Validate Configuration

  1. Read .claude/frontend-react-plugin.json
  2. If missing, tell the user to run /frontend-react-plugin:fe-init first and stop
  3. Extract baseDir from config

Step 1: Determine Scope

  • If argument provided: audit the specified file or directory
  • If no argument: audit all files in {baseDir}/

A missing or empty target is unverifiable, never a pass. Confirm the resolved target exists before launching the agent; if it does not, say so and stop. If the agent reports unverifiable, surface that verbatim — do not render it as a passing audit.

Step 2: Launch Security Auditor

Task(subagent_type: "security-auditor", prompt: "
  Audit frontend code for security vulnerabilities.

  Parameters:
  - targetPath: {targetPath}
  - projectRoot: {cwd}

  Follow the process defined in agents/security-auditor.md.
  Return the audit report as text.
")

Step 3: Display Report

Display the agent's text output directly. No further processing needed.

04 同仓库更多 Skills