← 返回 Skills 市场

OpenClaw Security Guard

Name: OpenClaw Security Guard
Author: x-rayluan

作者 X-RayLuan · GitHub ↗ · v0.2.1 · MIT-0

cross-platform ⚠ suspicious

274

总下载

当前安装

版本数

在 OpenClaw 中安装

/install clawlite-openclaw-security-guard

功能描述

This skill should be used when the user asks to harden agent workflows, audit prompts/commands/URLs/paths, scan a third-party skill before install or publish...

使用说明 (SKILL.md)

OpenClaw Security Guard

Use this skill to run fast local security checks before trusting or publishing automation.

What this skill is for

Run this skill when you need to:

scan suspicious text for prompt injection / secret leakage patterns
validate shell commands before automation or publishing
validate URLs for SSRF / localhost / metadata access risks
validate file paths for traversal / sensitive file access
audit a skill folder for dangerous scripts, hardcoded secrets, exfiltration patterns, or unsafe install/publish flows
add a lightweight self-defense layer before using external skills

Workflow

Choose the narrowest check needed.
Run one of the bundled scripts.
Treat BLOCK as stop-work until reviewed.
Treat WARN as requiring human review or a narrower sandbox.
For skill audits, review the flagged file lines before install/publish.

Bundled scripts

1) Quick text / command / URL / path checks

node {baseDir}/scripts/security-check.mjs text "\x3Ccontent>"
node {baseDir}/scripts/security-check.mjs command "\x3Cshell command>"
node {baseDir}/scripts/security-check.mjs url "\x3Curl>"
node {baseDir}/scripts/security-check.mjs path "\x3Cpath>"

2) Skill / folder audit

node {baseDir}/scripts/audit-skill-dir.mjs /absolute/or/relative/path/to/skill

3) Write audit into Obsidian vault

node {baseDir}/scripts/write-obsidian-audit.mjs /tmp/audit.json "Skill Audit - my-skill"

This writes a markdown audit note into the ClawLite Obsidian vault under Security Audits/.

4) Install lightweight local hook wrapper

bash {baseDir}/scripts/install-hooks.sh

This installs a reusable workspace script for prepublish checks.

This audits for:

hardcoded secrets / tokens
curl|bash / wget|sh installers
destructive shell patterns
risky exfiltration / webhook / netcat usage
suspicious file targets like ~/.ssh, /etc/passwd, .env, id_rsa

Verdicts

ALLOW — no high-risk pattern found in this lightweight pass
WARN — review manually before proceeding
BLOCK — do not trust / run / publish until reviewed

Important limits

This is a lightweight guard, not a full sandbox.
Regex-based detection catches common dangerous patterns, not all attacks.
A clean result does not prove safety.
For high-risk code, still prefer human review and runtime isolation.

Publishing / install guard

Before publishing or installing a skill from GitHub / ClawHub:

run audit-skill-dir.mjs
inspect every WARN / BLOCK
only proceed when the remaining risk is understood

References

If you need the audit categories / philosophy, read:

{baseDir}/references/checklist.md

安全使用建议

This skill appears to implement a useful local pre-publish/audit tool, but review it locally before running: 1) Ensure you have Node available (scripts rely on node but the skill metadata doesn't declare it). 2) Inspect write-obsidian-audit.mjs — it writes to a hard-coded path (/Users/m1/...) that likely belongs to the author; change it or delete that behavior before running to avoid unexpected writes. 3) The install-hooks.sh will create a script in $HOME/.openclaw/workspace — accept only if you want that helper installed. 4) Because the audit script reads files under whatever path you supply, avoid pointing it at sensitive system directories unless you intend to allow reading those files. 5) Prefer running the scripts in an isolated environment (container or throwaway account) and manually inspect the code (especially file-write locations) before giving the skill filesystem access. If you want higher assurance, ask the author to remove hard-coded paths and to declare Node as a required runtime.

功能分析

Type: OpenClaw Skill Name: clawlite-openclaw-security-guard Version: 0.2.1 The skill provides a suite of local security auditing tools designed to scan code, shell commands, URLs, and file paths for common vulnerabilities, hardcoded secrets, and malicious patterns. The core logic in scripts like audit-skill-dir.mjs and security-check.mjs uses regex-based detection to identify risks such as prompt injection, SSRF, and data exfiltration in other files. The installation script (install-hooks.sh) sets up a local prepublish wrapper, and the overall behavior is transparent and strictly aligned with its stated purpose as a security guard for the OpenClaw environment.

能力评估

ℹ Purpose & Capability

The skill's name, description, and scripts align: it scans text/commands/URLs/paths and audits skill folders. One mismatch: the package includes Node and bash scripts but the registry metadata lists no required binaries; a legitimate skill should declare Node (and/or bash) as a dependency/runtime requirement.

⚠ Instruction Scope

SKILL.md and scripts instruct the agent to read arbitrary target directories (audit-skill-dir) and to write audit notes to disk. write-obsidian-audit.mjs uses a hard-coded vault path (/Users/m1/Desktop/obsidianvault/ClawLite) which is a leak of the packager's local path and will attempt to write to that exact location when run — unexpected and undesirable. The install-hooks.sh writes a helper script into $HOME/.openclaw/workspace which modifies the user's home workspace; this is documented but is an automatic filesystem modification that users should be warned about.

✓ Install Mechanism

There is no remote download/install step; the skill ships its scripts in the package. That lowers supply-chain risk. The included install-hooks.sh does create a script in the user's $HOME which is a local change but not a remote installation.

ℹ Credentials

The skill does not request any environment variables or credentials (good). However, scripts write into $HOME and a hard-coded absolute path to an Obsidian vault; the latter is unrelated to the stated purpose and appears to be a leftover developer path. No secrets are requested, but the auditing scripts will read files under whatever target directory is provided (expected for an audit tool).

ℹ Persistence & Privilege

always:false (good). The only persistent change is install-hooks.sh which installs a helper script under $HOME/.openclaw/workspace — this is scope-limited to the user's workspace but it does modify the filesystem and create an executable helper. The skill does not attempt to modify other skills or global agent settings beyond that helper install.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install clawlite-openclaw-security-guard
安装完成后，直接呼叫该 Skill 的名称或使用 /clawlite-openclaw-security-guard 触发
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

v0.2.1

Align description with when-to-use trigger language and add keyword metadata.

v0.2.0

Add prepublish guard, Obsidian audit writer, and lightweight hook installer wrapper.

v0.1.0

Initial lightweight security guard for OpenClaw prompts, commands, URLs, paths, and skill-folder audits.

元数据

Slug clawlite-openclaw-security-guard

版本 0.2.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题