← 返回 Skills 市场
alvisdunlop

Alvis Security Auditor

作者 AlvisDunlop · GitHub ↗ · v1.0.5 · MIT-0
cross-platform ✓ 安全检测通过
76
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install alvis-security-auditor
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 to do what it says: a read-only audit of an OpenClaw deployment. Before using it, consider: 1) Run audits in a trusted environment or a snapshot/clone — some checks read system-wide files and logs that may contain sensitive tokens or PII. 2) Prefer running as a non-root user where feasible; some checks will be limited without elevated rights, but running as root increases exposure. 3) Do not share raw command outputs publicly; inspect and redact sensitive lines (the skill instructs redaction, but you should verify). 4) If you allow remediation, require explicit confirmation for each destructive command and consider performing fixes manually or in a controlled maintenance window. 5) If you need higher assurance about the skill's provenance, request the SKILL.md source or an author identity; the skill has no homepage or known owner metadata beyond an ID.
功能分析
Type: OpenClaw Skill Name: alvis-security-auditor Version: 1.0.5 The 'alvis-security-auditor' skill (SKILL.md) is a legitimate security auditing tool designed to inspect OpenClaw deployments for misconfigurations. It explicitly instructs the AI agent to operate in a read-only mode, redact any discovered secrets, and avoid making changes without user consent. The workflow uses standard diagnostic commands (e.g., ss, ps, find, journalctl) to identify risks like public network exposure, insecure file permissions, and outdated versions, aligning perfectly with its stated purpose.
能力评估
Purpose & Capability
The name/description (OpenClaw security audit) align with the actions requested in SKILL.md: enumerating processes, ports, configs, skills, permissions, logs, and credentials storage. There are no unrelated environment variables, binaries, or installs requested.
Instruction Scope
Instructions are explicitly read-only and focused on auditing OpenClaw (processes, configs, skills, ports, logs, permissions). However, several recommended commands (e.g., find / -perm -4000, journalctl, reading ~/.openclaw, scanning /etc/cron.*, systemctl) will access system-wide and potentially sensitive information; they often require elevated privileges to be meaningful. The skill tells the agent to redact secrets and not exfiltrate data, but it grants broad discretion to enumerate host state which can expose secrets if outputs are transmitted off-host.
Install Mechanism
No install spec and no code files — the skill is instruction-only, which minimizes installation risk. Nothing will be downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths in its metadata. The SKILL.md instructs reading local config files (e.g., ~/.openclaw/config.json) and logs, which is proportionate for an auditor but does involve access to sensitive local state — the instructions acknowledge redaction and read-only policy.
Persistence & Privilege
Flags show default privileges (always:false, agent invocation allowed). The skill does not request permanent presence or attempt to modify other skills or system settings; remediation actions are only to be taken after explicit user approval per the instructions.
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-auditor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /alvis-security-auditor 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
v1.0.5
**Skill renamed and documentation majorly expanded to focus on read-only, actionable security audits of OpenClaw/Clawdbot environments.** - Skill name changed to `openclaw-security-audit`, focusing specifically on OpenClaw, Clawdbot, and Moltbot deployments. - Comprehensive, step-by-step audit workflow added, detailing required commands and types of findings for 10 specific security domains (e.g., network exposure, credential leakage, privilege escalation, skill risks). - Mandates read-only mode by default: no config changes or secret exfiltration, with clear instructions to redact secrets from reports. - Standardized, terminal-style audit report format introduced, with explicit reporting for every check (OK/VULNERABLE/UNKNOWN) and actionable fixes for each vulnerability. - Includes summary report section and guidance on only performing remediation after explicit user request.
元数据
Slug alvis-security-auditor
版本 1.0.5
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Alvis Security Auditor 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 76 次。

如何安装 Alvis Security Auditor?

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

Alvis Security Auditor 是免费的吗?

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

Alvis Security Auditor 支持哪些平台?

Alvis Security Auditor 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 Alvis Security Auditor?

由 AlvisDunlop(@alvisdunlop)开发并维护,当前版本 v1.0.5。

💬 留言讨论