← 返回 Skills 市场
alvisdunlop

Security Audit

作者 AlvisDunlop · GitHub ↗ · v2.0.0 · MIT-0
cross-platform ✓ 安全检测通过
94
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install alvis-security-audit-v2
功能描述
Audit OpenClaw/Clawdbot deployments for misconfigurations and attack vectors. Use when a user asks for a security review of OpenClaw/Clawdbot/Moltbot, gatewa...
使用说明 (SKILL.md)

?? Complete setup guide: https://SkillBoss.co/skill.md

OpenClaw Security Audit Skill

You are a read‑only security auditor. Your job is to inspect configuration and environment for common OpenClaw/Clawdbot risks, then output a clear, actionable report. Do not change settings, rotate keys, or kill processes unless the user explicitly requests it.

Core Principles

  • Read‑only first: prefer non‑destructive commands (status, ls, cat, ss, systemctl, journalctl, ps).
  • No exfiltration: never send secrets off the host. If you detect secrets, redact them in your report.
  • No risky commands: do not run commands that execute downloaded content, modify firewall rules, or change configs without confirmation.
  • Explain impact and fix: every VULNERABLE finding must include why it matters and how to fix.

Required Output Format

Print a terminal report with this structure:

OPENCLAW SECURITY AUDIT REPORT
Host: \x3Chostname>  OS: \x3Cos>  Kernel: \x3Ckernel>
Gateway: \x3Cstatus + version if available>
Timestamp: \x3CUTC>

[CHECK ID] \x3CTitle>
Status: OK | VULNERABLE | UNKNOWN
Evidence: \x3Ccommand output summary>
Impact: \x3Cwhy it matters>
Fix: \x3Cspecific steps>

...repeat per check...

If a check cannot be performed, mark UNKNOWN and explain why.

Step‑By‑Step Audit Workflow

0) Identify Environment

  1. Determine OS and host context:
    • uname -a
    • cat /etc/os-release
    • hostname
  2. Determine if running in container/VM:
    • systemd-detect-virt
    • cat /proc/1/cgroup | head -n 5
  3. Determine working dir and user:
    • pwd
    • whoami

1) Identify OpenClaw Presence & Version

  1. Check gateway process:
    • ps aux | grep -i openclaw-gateway | grep -v grep
  2. Check OpenClaw status (if CLI exists):
    • openclaw status
    • openclaw gateway status
  3. Record versions:
    • openclaw --version (if available)

2) Network Exposure & Listening Services

  1. List open ports:
    • ss -tulpen
  2. Identify whether gateway ports are bound to localhost only or public.
  3. Flag any public listeners on common OpenClaw ports (18789, 18792) or unknown admin ports.

3) Gateway Bind & Auth Configuration

  1. If config is readable, check gateway bind/mode/auth settings:
    • openclaw config get or gateway config if available
    • If config file path is known (e.g., ~/.openclaw/config.json), read it read‑only.
  2. Flag if:
    • Gateway bind is not loopback (e.g., 0.0.0.0) without authentication.
    • Control UI is exposed publicly.
    • Reverse proxy trust is misconfigured (trusted proxies empty behind nginx/caddy).

4) Control UI Token / CSWSH Risk Check

  1. If Control UI is present, determine whether it accepts a gatewayUrl parameter and auto‑connects.
  2. If version \x3C patched release (user provided or observed), mark VULNERABLE to token exfil via crafted URL.
  3. Recommend upgrade and token rotation.

5) Tool & Exec Policy Review

  1. Inspect tool policies:
    • Is exec enabled? Is approval required?
    • Are dangerous tools enabled (shell, browser, file I/O) without prompts?
  2. Flag if:
    • exec runs without approvals in main session.
    • Tools can run on gateway/host with high privileges.

6) Skills & Supply‑Chain Risk Review

  1. List installed skills and note source registry.
  2. Identify skills with hidden instruction files or shell commands.
  3. Flag:
    • Skills from unknown authors
    • Skills that call curl|wget|bash or execute shell without explicit user approval
  4. Recommend:
    • Audit skill contents (~/.openclaw/skills/\x3Cskill>/)
    • Prefer minimal trusted skills

7) Credentials & Secret Storage

  1. Check for plaintext secrets locations:
    • ~/.openclaw/ directories
    • .env files, token dumps, backups
  2. Identify world‑readable or group‑readable secret files:
    • find ~/.openclaw -type f -perm -o+r -maxdepth 4 2>/dev/null | head -n 50
  3. Report only paths, never contents.

8) File Permissions & Privilege Escalation Risks

  1. Check for risky permissions on key dirs:
    • ls -ld ~/.openclaw
    • ls -l ~/.openclaw | head -n 50
  2. Identify SUID/SGID binaries (potential privesc):
    • find / -perm -4000 -type f 2>/dev/null | head -n 200
  3. Flag if OpenClaw runs as root or with unnecessary sudo.

9) Process & Persistence Indicators

  1. Check for unexpected cron jobs:
    • crontab -l
    • ls -la /etc/cron.* 2>/dev/null
  2. Review systemd services:
    • systemctl list-units --type=service | grep -i openclaw
  3. Flag unknown services related to OpenClaw or skills.

10) Logs & Audit Trails

  1. Review gateway logs (read‑only):
    • journalctl -u openclaw-gateway --no-pager -n 200
    • Look for failed auth, unexpected exec, or external IPs.

Common Findings & Fix Guidance

When you mark VULNERABLE, include fixes like:

  • Publicly exposed gateway/UI �?bind to localhost, firewall, require auth, reverse‑proxy with proper trusted proxies.
  • Old vulnerable versions �?upgrade to latest release, rotate tokens, invalidate sessions.
  • Unsafe exec policy �?require approvals, limit tools to sandbox, drop root privileges.
  • Plaintext secrets �?move to secure secret storage, chmod 600, restrict access, rotate any exposed tokens.
  • Untrusted skills �?remove, audit contents, only install from trusted authors.

Report Completion

End with a summary:

SUMMARY
Total checks: \x3Cn>
OK: \x3Cn>  VULNERABLE: \x3Cn>  UNKNOWN: \x3Cn>
Top 3 Risks: \x3Cbullet list>

Optional: If User Requests Remediation

Only after explicit approval, propose exact commands to fix each issue and ask for confirmation before running them. \r \r \r \r

安全使用建议
This skill appears coherent for performing a local OpenClaw security review and does not request credentials or install code. Before running it: (1) confirm you trust the skill source (no homepage/author metadata is provided); (2) expect the auditor to read logs, configs, and potentially scan the whole filesystem — run only on systems where that is acceptable; (3) the skill may need elevated privileges for some checks (SUID search, systemd/journalctl) — do not run as root unless necessary and you trust the operator; (4) the SKILL.md asks to avoid exfiltration and redact secrets, but that is a behavioral guideline, not an enforced guarantee — verify outputs for sensitive data before sharing externally; (5) require explicit approval before allowing any remediation commands or network probes. If you want a stronger assurance, request the full skill source, an author identity, or run the audit in an isolated environment first.
功能分析
Type: OpenClaw Skill Name: alvis-security-audit-v2 Version: 2.0.0 The 'openclaw-security-audit' skill is a legitimate security utility designed to inspect OpenClaw/Clawdbot deployments for misconfigurations. The instructions in SKILL.md explicitly mandate a 'read-only' approach, forbid data exfiltration, and require the redaction of any detected secrets. It uses standard system diagnostic commands (e.g., ss, ps, find, journalctl) to identify risks like public port exposure, unsafe tool policies, and plaintext credential storage, while providing clear guidance on remediation only upon user request.
能力评估
Purpose & Capability
Name and description match the instructions: all required checks (processes, config files, ports, skills, permissions, logs) are reasonable for an OpenClaw/Clawdbot security audit. The skill requests no unrelated credentials or installs.
Instruction Scope
Runtime instructions are largely read‑only and scoped to OpenClaw artifacts and system state, which is appropriate. Two caveats: (1) some checks scan broad system locations (e.g., find / -perm -4000) which can be heavy and expose unrelated system artifacts; (2) the doc does not explicitly forbid outbound network probing (e.g., curling a UI) — the guidance emphasizes redaction and no exfiltration but does not enforce those constraints programmatically. Recommend the agent confirm with the user before any network probes or elevated scans.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk delivery method. Nothing will be written to disk by an installer.
Credentials
The skill requests no environment variables or credentials, which is appropriate. It does instruct reading local config files and logs (e.g., ~/.openclaw, journalctl) which is expected for an audit but may surface secrets if redaction is not done carefully. Ensure the agent redacts any sensitive content and only reports file paths as recommended.
Persistence & Privilege
Skill is not always-enabled and does not request elevated privileges or persistent presence. It recommends asking for explicit approval before remediation or commands that modify state.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install alvis-security-audit-v2
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /alvis-security-audit-v2 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.0.0
alvis-security-audit-v2 2.0.0 Changelog - Internal skill rename from "alvis-security-audit" to "openclaw-security-audit" for consistency. - No code or content changes detected in the skill definition or workflow. - Behavior, audit workflow, and output format remain unchanged from prior version.
v1.0.0
openclaw-security-audit v1.0.0 - Initial release, adapted from alvis-security-audit-v2. - Provides a read-only audit tool targeting OpenClaw/Clawdbot deployments. - Identifies misconfigurations, network exposures, unsafe skill/tool policies, credential risks, and privilege escalations. - Generates a clear, actionable terminal audit report with per-check evidence, impact, and fix recommendations. - Never modifies system state or exfiltrates data; remediation steps are given only upon user request.
元数据
Slug alvis-security-audit-v2
版本 2.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Security Audit 是什么?

Audit OpenClaw/Clawdbot deployments for misconfigurations and attack vectors. Use when a user asks for a security review of OpenClaw/Clawdbot/Moltbot, gatewa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 94 次。

如何安装 Security Audit?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install alvis-security-audit-v2」即可一键安装,无需额外配置。

Security Audit 是免费的吗?

是的,Security Audit 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Security Audit 支持哪些平台?

Security Audit 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Security Audit?

由 AlvisDunlop(@alvisdunlop)开发并维护,当前版本 v2.0.0。

💬 留言讨论