数据库审计
- 作者仓库星标 1,187
- 叉子 185
- 作者更新于 2026年6月14日 10:01
- 作者仓库 claude-code-skills
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @daymade · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 需要 · OpenAI / Gemini / AWS
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- Deno
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 读取环境变量
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: repomix-safe-mixer
description: Safely package codebases with repomix by automatically detecting and removing hardcoded credenti…
category: 通用
runtime: Deno
---
# repomix-safe-mixer 输出预览
## PART A: 任务判断
- 适用问题:通用任务拆解、检查和交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Overview / Core Workflow / Standard Safe Packaging”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于通用任务拆解、检查和交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Overview / Core Workflow / Standard Safe Packaging”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、读取环境变量、会按任务需要访问外部网络、需要准备 OpenAI / Gemini / AWS API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、读取环境变量;会按任务需要访问外部网络;需要准备 OpenAI / Gemini / AWS API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、读取环境变量。
先用一个小任务确认它会围绕“Overview / Core Workflow / Standard Safe Packaging”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: repomix-safe-mixer
description: Safely package codebases with repomix by automatically detecting and removing hardcoded credenti…
category: 通用
source: daymade/claude-code-skills
---
# repomix-safe-mixer
## 什么时候使用
- repomix-safe-mixer 是一个通用扩展技能,按 SKILL 适合处理通用任务拆解、检查、交付和复盘,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的…
- 面向通用任务拆解、检查和交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Overview / Core Workflow / Standard Safe Packaging」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、读取环境变量;会按任务需要访问外部网络;需要准备 OpenAI / Gemini / AWS API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "repomix-safe-mixer" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Overview / Core Workflow / Standard Safe Packaging
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Deno | 读取文件、写入/修改文件、读取环境变量 | 会按任务需要访问外部网络
安全层 -> 需要准备 OpenAI / Gemini / AWS API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Repomix Safe Mixer
Overview
Safely package codebases with repomix by automatically detecting and removing hardcoded credentials.
This skill prevents accidental credential exposure when packaging code with repomix. It scans for hardcoded secrets (API keys, database credentials, tokens), reports findings, and ensures safe packaging.
When to use: When packaging code with repomix for distribution, creating shareable reference packages, or whenever security concerns exist about hardcoded credentials in code.
Core Workflow
Standard Safe Packaging
Use safe_pack.py from this skill's scripts/ directory for the complete workflow: scan → report → pack.
python3 scripts/safe_pack.py <directory>
What it does:
- Scans directory for hardcoded credentials
- Reports findings with file/line details
- Blocks packaging if secrets found
- Packs with repomix only if scan is clean
Example:
python3 scripts/safe_pack.py ./my-project
Output if clean:
🔍 Scanning ./my-project for hardcoded secrets...
✅ No secrets detected!
📦 Packing ./my-project with repomix...
✅ Packaging complete!
Package is safe to distribute.
Output if secrets found:
🔍 Scanning ./my-project for hardcoded secrets...
⚠️ Security Scan Found 3 Potential Secrets:
🔴 supabase_url: 1 instance(s)
- src/client.ts:5
Match: https://your-project-ref.supabase.co
❌ Cannot pack: Secrets detected!
Options
Custom output file:
python3 scripts/safe_pack.py \
./my-project \
--output package.xml
With repomix config:
python3 scripts/safe_pack.py \
./my-project \
--config repomix.config.json
Exclude patterns from scanning:
python3 scripts/safe_pack.py \
./my-project \
--exclude '.*test.*' '.*\.example'
Force pack (dangerous, skip scan):
python3 scripts/safe_pack.py \
./my-project \
--force # ⚠️ NOT RECOMMENDED
Standalone Secret Scanning
Use scan_secrets.py from this skill's scripts/ directory for scanning only (without packing).
python3 scripts/scan_secrets.py <directory>
Use cases:
- Verify cleanup after removing credentials
- Pre-commit security checks
- Audit existing codebases
Example:
python3 scripts/scan_secrets.py ./my-project
JSON output for programmatic use:
python3 scripts/scan_secrets.py \
./my-project \
--json
Exclude patterns:
python3 scripts/scan_secrets.py \
./my-project \
--exclude '.*test.*' '.*example.*' '.*SECURITY_AUDIT\.md'
Detected Secret Types
The scanner detects common credential patterns including:
Cloud Providers:
- AWS Access Keys (
AKIA...) - Cloudflare R2 Account IDs and Access Keys
- Supabase Project URLs and Anon Keys
API Keys:
- Stripe Keys (
sk_live_...,pk_live_...) - OpenAI API Keys (
sk-...) - Google Gemini API Keys (
AIza...) - Generic API Keys
Authentication:
- JWT Tokens (
eyJ...) - OAuth Client Secrets
- Private Keys (
-----BEGIN PRIVATE KEY-----) - Turnstile Keys (
0x...)
See references/common_secrets.md for complete list and patterns.
Handling Detected Secrets
When secrets are found:
Step 1: Review Findings
Examine each finding to verify it's a real credential (not a placeholder or example).
Step 2: Replace with Environment Variables
Before:
const SUPABASE_URL = "https://your-project-ref.supabase.co";
const API_KEY = "<hardcoded-anon-key-DO-NOT-COMMIT>";
After:
const SUPABASE_URL = import.meta.env.VITE_SUPABASE_URL || "https://your-project-ref.supabase.co";
const API_KEY = import.meta.env.VITE_API_KEY || "your-api-key-here";
// Validation
if (!import.meta.env.VITE_SUPABASE_URL) {
console.error("⚠️ Missing VITE_SUPABASE_URL environment variable");
}
Step 3: Create .env.example
# Example environment variables
VITE_SUPABASE_URL=https://your-project-ref.supabase.co
VITE_API_KEY=your-api-key-here
# Instructions:
# 1. Copy this file to .env
# 2. Replace placeholders with real values
# 3. Never commit .env to version control
Step 4: Verify Cleanup
Run scanner again to confirm secrets removed:
python3 scripts/scan_secrets.py ./my-project
Step 5: Safe Pack
Once clean, package safely:
python3 scripts/safe_pack.py ./my-project
Post-Exposure Actions
If credentials were already exposed (e.g., committed to git, shared publicly):
- Rotate credentials immediately - Generate new keys/tokens
- Revoke old credentials - Disable compromised credentials
- Audit usage - Check logs for unauthorized access
- Monitor - Set up alerts for unusual activity
- Update deployment - Deploy code with new credentials
- Document incident - Record what was exposed and actions taken
Common False Positives
The scanner skips common false positives:
Placeholders:
your-api-key,example-key,placeholder-value<YOUR_API_KEY>,${API_KEY},TODO: add key
Test/Example files:
- Files matching
.*test.*,.*example.*,.*sample.*
Comments:
- Lines starting with
//,#,/*,*
Environment variable references (correct usage):
process.env.API_KEYimport.meta.env.VITE_API_KEYDeno.env.get('API_KEY')
Use --exclude to skip additional patterns if needed.
Integration with Repomix
This skill works with standard repomix:
Default usage (no config):
python3 scripts/safe_pack.py ./project
With repomix config:
python3 scripts/safe_pack.py \
./project \
--config repomix.config.json
Custom output location:
python3 scripts/safe_pack.py \
./project \
--output ~/Downloads/package-clean.xml
The skill runs repomix internally after security validation, passing through config and output options.
Example Workflows
Workflow 1: Package a Clean Project
# Scan and pack in one command
python3 scripts/safe_pack.py \
~/workspace/my-project \
--output ~/Downloads/my-project-package.xml
Workflow 2: Clean and Package a Project with Secrets
# Step 1: Scan to discover secrets
python3 scripts/scan_secrets.py ~/workspace/my-project
# Step 2: Review findings and replace credentials with env vars
# (Edit files manually or with automation)
# Step 3: Verify cleanup
python3 scripts/scan_secrets.py ~/workspace/my-project
# Step 4: Package safely
python3 scripts/safe_pack.py \
~/workspace/my-project \
--output ~/Downloads/my-project-clean.xml
Workflow 3: Audit Before Commit
# Pre-commit hook: scan for secrets
python3 scripts/scan_secrets.py . --json
# Exit code 1 if secrets found (blocks commit)
# Exit code 0 if clean (allows commit)
Resources
References:
references/common_secrets.md- Complete credential pattern catalog
Scripts:
scripts/scan_secrets.py- Standalone security scannerscripts/safe_pack.py- Complete scan → pack workflow
Related Skills:
repomix-unmixer- Extracts files from repomix packagesskill-creator- Creates new Claude Code skills
Security Note
This skill detects common patterns but may not catch all credential types. Always:
- Review findings manually
- Rotate exposed credentials
- Use .env.example templates
- Validate environment variables
- Monitor for unauthorized access
Not a replacement for: Secret scanning in CI/CD, git history scanning, or comprehensive security audits.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核