Token导航 LogoToken导航

Agent Skill · 研究检索

envguard(envguard 搜索)

envguard 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

envguard 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 33,416。

总安装 2,352周安装 98GitHub Stars 公开资料未说明下载 784核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:envguard(envguard 搜索)
来源仓库:https://github.com/suhteevah/envguard
安装命令:
openclaw skills install envguard
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install envguard

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于预提交秘密检测,防止凭证、API 密钥和 .env 文件泄露到代码库。适合在开发流程中快速识别潜在的安全风险和配置漏洞。通过 OpenClaw 的 clawhub 安装,调用时需确认是否具备扫描权限和文件访问能力。不能替代人工复核,涉及生产数据时应先脱敏并限制操作范围。建议查阅仓库文档以了解支持的规则集和集成方式。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install envguard;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

envguard 怎么安装?

在终端执行 openclaw skills install envguard。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

envguard 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

envguard 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

envguard 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

envguard 用的人多吗?

公开数据是累计安装 2,352 次,近一周安装 98 次,下载 784 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

envguard 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
envguard

envguard 搜索 · 本页

2,352—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
envguard
description
Pre-commit secret detection — block leaked credentials, API keys, and .env files before they hit git
homepage
https://envguard.pages.dev
metadata
user-invocable
true
disable-model-invocation
false

EnvGuard — Pre-Commit Secret Detection

EnvGuard scans your code for leaked secrets, credentials, API keys, and .env file contents before they reach git. It uses regex-based pattern matching against 50+ secret formats from 20+ services, lefthook for git hook integration, and produces SARIF-compatible reports for compliance workflows.

Commands

Free Tier (No license required)

envguard scan [file|directory]

One-shot secret scan of files or directories.

How to execute:

bash "<SKILL_DIR>/scripts/envguard.sh" scan [target]

What it does:

  1. Accepts a file path or directory (defaults to current directory)
  2. Finds all text files (excluding .git/, node_modules/, dist/, build/, vendor/, __pycache__)
  3. Runs 50+ secret detection patterns against each file
  4. Respects .envguardignore exclusions (gitignore syntax)
  5. Outputs findings with: file, line number, pattern matched, severity, redacted match
  6. Exit code 0 if clean, exit code 1 if critical/high findings detected

Example usage scenarios:

  • "Scan this repo for leaked secrets" -> runs envguard scan .
  • "Check this file for API keys" -> runs envguard scan src/config.ts
  • "Are there any secrets in my source code?" -> runs envguard scan src/

Pro Tier ($19/user/month -- requires ENVGUARD_LICENSE_KEY)

envguard hooks install

Install git pre-commit hooks that scan staged files for secrets before every commit.

How to execute:

bash "<SKILL_DIR>/scripts/envguard.sh" hooks install

What it does:

  1. Validates Pro+ license
  2. Copies lefthook config to project root
  3. Installs lefthook pre-commit hook
  4. On every commit: scans all staged files for secrets, blocks commit if secrets found, shows remediation advice
envguard hooks uninstall

Remove EnvGuard git hooks.

bash "<SKILL_DIR>/scripts/envguard.sh" hooks uninstall
envguard allowlist [add|remove|list] [pattern]

Manage false positive patterns. Allowlisted patterns are skipped during scanning.

bash "<SKILL_DIR>/scripts/envguard.sh" allowlist add "EXAMPLE_API_KEY_FOR_TESTS"
bash "<SKILL_DIR>/scripts/envguard.sh" allowlist remove "EXAMPLE_API_KEY_FOR_TESTS"
bash "<SKILL_DIR>/scripts/envguard.sh" allowlist list

What it does:

  1. Validates Pro+ license
  2. Reads/writes allowlist in ~/.openclaw/openclaw.json (envguard.config.allowlist)
  3. Allowlisted patterns are treated as known-safe and skipped during scans
envguard diff

Scan only staged changes (git diff --cached) for secrets.

bash "<SKILL_DIR>/scripts/envguard.sh" diff

What it does:

  1. Validates Pro+ license
  2. Gets staged changes via git diff --cached
  3. Scans only added/modified lines for secrets
  4. Ideal for pre-commit checks on large repos

Team Tier ($39/user/month -- requires ENVGUARD_LICENSE_KEY with team tier)

envguard history [directory]

Full git history scan -- finds secrets in all previous commits.

bash "<SKILL_DIR>/scripts/envguard.sh" history [directory]

What it does:

  1. Validates Team+ license
  2. Walks entire git log using git log -p
  3. Scans every diff for secrets across all commits
  4. Reports: commit hash, author, date, file, line, pattern matched
  5. Critical for onboarding repos that may have had secrets committed in the past
envguard report [directory]

Generate a SARIF-compatible or markdown compliance report.

bash "<SKILL_DIR>/scripts/envguard.sh" report [directory]

What it does:

  1. Validates Team+ license
  2. Runs full scan of the directory
  3. Generates a formatted markdown report with severity breakdown
  4. Includes remediation steps for each finding category
  5. Output suitable for compliance audits and security reviews
envguard policy [directory]

Custom secret patterns and enforcement rules.

bash "<SKILL_DIR>/scripts/envguard.sh" policy [directory]

What it does:

  1. Validates Team+ license
  2. Loads custom patterns from ~/.openclaw/openclaw.json (envguard.config.customPatterns)
  3. Enforces organization-specific secret rules (e.g., internal token formats)
  4. Combines custom patterns with built-in patterns for comprehensive scanning

Detected Secret Types

EnvGuard detects 50+ secret patterns across 20+ services:

CategoryExamplesSeverity
AWS CredentialsAKIA* keys, aws_secret_access_keyCritical
Stripe Keyssk_live_*, sk_test_*, rk_live_*, whsec_*Critical
GitHub Tokensghp_*, gho_*, ghu_*, ghs_*, ghr_*Critical
GitLab Tokensglpat-*Critical
Private KeysRSA, OPENSSH, DSA, EC, PGP private keysCritical
Slack Tokensxoxb-*, xoxp-*, xoxo-*, xapp-*High
Google API KeysAIza*High
JWT TokenseyJ* (long base64 tokens)High
Database URIspostgres://, mysql://, mongodb://, redis://High
Twilio KeysSK* account SIDsHigh
SendGrid KeysSG.*High
Firebase/SupabaseAPI keys and service tokensHigh
npm Tokensnpm_*High
Heroku API KeysHeroku token patternsMedium
DigitalOceandop_v1_*, doo_v1_*Medium
Azure KeysAzure subscription/account keysMedium
CloudflareAPI tokens and keysMedium
Docker HubDocker auth tokensMedium
Mailgun/PostmarkAPI keysMedium
Generic Secretsapi_key=, password=, secret=, token=Low
.env LeaksKEY=value patterns in source filesLow

Configuration

Users can configure EnvGuard in ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "envguard": {
        "enabled": true,
        "apiKey": "YOUR_LICENSE_KEY_HERE",
        "config": {
          "severityThreshold": "high",
          "allowlist": [],
          "customPatterns": [],
          "excludePatterns": ["**/node_modules/**", "**/dist/**", "**/.git/**"],
          "reportFormat": "markdown"
        }
      }
    }
  }
}

Important Notes

  • Free tier works immediately with no configuration
  • All scanning happens locally -- no code or secrets are sent to external servers
  • License validation is offline -- no phone-home or network calls
  • Supports .envguardignore files (gitignore syntax) to exclude paths
  • Matches are always redacted in output (first/last 4 chars only)
  • Git hooks use lefthook which must be installed (see install metadata above)
  • Exit codes: 0 = clean, 1 = findings detected (for CI/CD integration)

Error Handling

  • If lefthook is not installed and user tries hooks install, prompt to install it
  • If license key is invalid or expired, show clear message with link to https://envguard.pages.dev/renew
  • If a file is binary, skip it automatically with no warning
  • If .envguardignore is malformed, warn and continue with default excludes
  • If no files found in target, report clean scan with info message

When to Use EnvGuard

The user might say things like:

  • "Scan for leaked secrets"
  • "Check if any API keys are in my code"
  • "Set up secret scanning on my commits"
  • "Are there any credentials in this repo?"
  • "Generate a security report for compliance"
  • "Scan git history for leaked passwords"
  • "Block secrets from being committed"
  • "Check my staged files for secrets"
  • "Add a false positive to the allowlist"

平台分布

OpenClaw

84.96%
按下载量换算666

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills