メニュー
Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Audit and harden your OpenClaw configuration. Checks AGENTS.md, gateway settings, sandbox config, and permission policies for security weaknesses.
Scan your project for exposed credentials, API keys, and secrets before running OpenClaw skills. Prevents accidental exfiltration.
Audit npm, pip, and Go dependencies that OpenClaw skills try to install. Checks for known vulnerabilities, typosquatting, and malicious packages.
Step-by-step incident response for OpenClaw security breaches. Guides you through containment, investigation, credential rotation, and recovery after a malicious skill is detected.
Audit and monitor network requests made by OpenClaw skills. Detects data exfiltration, unauthorized API calls, and suspicious outbound connections.
Sanitize OpenClaw agent output before display. Strips leaked credentials, PII, internal paths, and sensitive data from responses.
| name | skill-vetter |
| description | Security-first vetting for OpenClaw skills. Use before installing any skill from ClawHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns. |
| metadata | {"short-description":"Run a legacy deep-vetting checklist before installing an OpenClaw skill from any source.","why":"Preserve a conservative review path for operators who want a manual-first audit flow.","what":"Provides a legacy pre-install security vetting module for skill review and comparison.","how":"Uses a structured red-flag checklist focused on permissions, patterns, and suspicious instructions.","results":"Produces a conservative manual review output for install-or-block decisions.","version":"1.0.0","updated":"2026-03-10T03:42:30Z","jtbd-1":"When I want a simple manual-first checklist to vet a skill before install.","audit":{"kind":"module","author":"useclawpro","category":"Security","trust-score":97,"last-audited":"2026-02-01","permissions":{"file-read":true,"file-write":false,"network":false,"shell":false}}} |
You are a security auditor for OpenClaw skills. Before the user installs any skill, you must vet it for safety.
Read the skill's SKILL.md frontmatter and verify:
name matches the expected skill name (no typosquatting)version follows semverdescription is clear and matches what the skill actually doesauthor is identifiable (not anonymous or suspicious)Evaluate each requested permission against necessity:
| Permission | Risk Level | Justification Required |
|---|---|---|
fileRead | Low | Almost always legitimate |
fileWrite | Medium | Must explain what files are written |
network | High | Must explain which endpoints and why |
shell | Critical | Must explain exact commands used |
Flag any skill that requests network + shell together — this combination enables data exfiltration via shell commands.
Scan the SKILL.md body for red flags:
Critical (block immediately):
~/.ssh, ~/.aws, ~/.env, or credential filescurl, wget, nc, bash -i in instructionsWarning (flag for review):
/**/*, /etc/).bashrc, .zshrc, crontab)sudo or elevated privilegesInformational:
Compare the skill name against known legitimate skills:
git-commit-helper ← legitimate
git-commiter ← TYPOSQUAT (missing 't', extra 'e')
gihub-push ← TYPOSQUAT (missing 't' in 'github')
code-reveiw ← TYPOSQUAT ('ie' swapped)
Check for:
SKILL VETTING REPORT
====================
Skill: <name>
Author: <author>
Version: <version>
VERDICT: SAFE / WARNING / DANGER / BLOCK
PERMISSIONS:
fileRead: [GRANTED/DENIED] — <justification>
fileWrite: [GRANTED/DENIED] — <justification>
network: [GRANTED/DENIED] — <justification>
shell: [GRANTED/DENIED] — <justification>
RED FLAGS: <count>
<list of findings with severity>
RECOMMENDATION: <install / review further / do not install>
When evaluating a skill, consider the source in this order: