菜单
Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, supply chain, credentials, injection defense, compliance, and incident response.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | openclaw-security |
| description | Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, supply chain, credentials, injection defense, compliance, and incident response. |
| user-invocable | true |
| metadata | {"openclaw":{"emoji":"🔒","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}} |
One skill to install, configure, and orchestrate the entire OpenClaw security stack.
python3 {baseDir}/scripts/security.py install --workspace /path/to/workspace
Installs all 11 free security skills from ClawHub.
python3 {baseDir}/scripts/security.py status --workspace /path/to/workspace
Aggregated health check across all installed security tools.
python3 {baseDir}/scripts/security.py scan --workspace /path/to/workspace
Runs every scanner: integrity verification, secret detection, permission audit, network DLP, supply chain analysis, injection scanning, credential exposure, and compliance audit.
python3 {baseDir}/scripts/security.py setup --workspace /path/to/workspace
Initializes all tools that need it: integrity baseline, skill signing, audit ledger, compliance policy.
python3 {baseDir}/scripts/security.py update --workspace /path/to/workspace
Updates all installed security skills to latest versions via ClawHub.
python3 {baseDir}/scripts/security.py list --workspace /path/to/workspace
Shows which security tools are installed and their versions.
python3 {baseDir}/scripts/security.py protect --workspace /path/to/workspace
Runs automated countermeasures across all installed Pro tools. Requires Pro versions.
| Tool | Domain | Free | Pro |
|---|---|---|---|
| warden | Workspace integrity, injection detection | Detect | Restore, rollback, quarantine |
| sentry | Secret/credential scanning | Detect | Redact, quarantine |
| arbiter | Permission auditing | Detect | Revoke, enforce |
| egress | Network DLP, exfiltration detection | Detect | Block, allowlist |
| ledger | Hash-chained audit trail | Record | Freeze, forensics |
| signet | Cryptographic skill signing | Verify | Reject, restore |
| sentinel | Supply chain security | Scan | Quarantine, block |
| vault | Credential lifecycle | Audit | Fix, rotate |
| bastion | Prompt injection defense | Scan | Sanitize, enforce |
| marshal | Compliance/policy enforcement | Audit | Enforce, hooks |
| triage | Incident response & forensics | Investigate | Contain, remediate |
Normalize palette and formatting in local image assets.
Remove hidden metadata from local SVG files for safer reuse.
Optimize local SVG files while staying inside the current image task.
Download and install skills from ClawHub (https://clawhub.ai). Use when user wants to browse, search, or download skills from the ClawHub skill registry.
Use this skill when users need help finding, discovering, or selecting OpenClaw skills from the Clawhub marketplace. Triggers include: '哪个技能适合', '怎么找到', '技能搜索', 'skill search', 'how to find skill', or any request about navigating the 238+ skill ecosystem. Helps users match their tasks to appropriate skills and understand skill capabilities.
OpenClaw扩展安全管理系统。扫描已安装扩展的安全风险，提供allowlist策略控制，在使用高风险扩展前进行风险提示。适用于安全管理、风险评估、权限控制场景。