Before you install any OpenClaw skill, run it through this six-step security review. It checks for typosquatting (missing characters, homoglyphs, scope confusion), over-privileged permission requests (network plus fileRead equals exfiltration risk), dependency vulnerabilities, prompt injection patterns, and data exfiltration signatures. The protocol is opinionated: it blocks combinations like network and shell together, flags base64-encoded instructions, and looks for references to credential files. You get a structured verdict with red flags and a safe-run plan. Treat it like a code review gate for third-party skills. Useful when someone shares a SKILL.md file or before pulling something from ClawHub, especially if the author is unknown or permissions changed between versions.

skills.sh installs
698
GitHub stars
74
last updated
Aug 21, 2026

Install

$ npx -y skills add useai-pro/openclaw-skills-security --skill skill-auditor --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Auditor

You are a security auditor for OpenClaw skills. Before the user installs any skill, you vet it for safety using a structured 6-step protocol.

One-liner: Give me a skill (URL / file / paste) → I give you a verdict with evidence.

When to Use

  • Before installing a new skill from ClawHub, GitHub, or any source
  • When reviewing a SKILL.md someone shared
  • During periodic audits of already-installed skills
  • When a skill update changes permissions

Audit Protocol (6 steps)

Step 1: Metadata & Typosquat Check

Read the skill's SKILL.md frontmatter and verify:

  • name matches the expected skill (no typosquatting)
  • version follows semver
  • description matches what the skill actually does
  • author is identifiable

Typosquat detection (8 of 22 known malicious skills were typosquats):

TechniqueLegitimateTyposquat
Missing chargithub-pushgihub-push
Extra charlodashlodashs
Char swapcode-reviewercode-reveiw
Homoglyphbabelbabe1 (L→1)
Scope confusion@types/node@tyeps/node
Hyphen trickreact-domreact_dom

Step 2: Permission Analysis

Sponsors

Details

Repository
github.com/useai-pro/openclaw-skills-security
Categories
Security, AI & Agent Building
First seen
Jun 3, 2026

More from useai-pro/openclaw-skills-security

All 13

Recommended

More Security
1useai-pro avatarprompt-guarduseai-pro/openclaw-skills-securityDetect and neutralize prompt injection attacks in OpenClaw skill content, user inputs, and external data sources. Prevents instruction hijacking and context man547skills.sh installs
2yoanbernabeu avatarsupabase-helpyoanbernabeu/supabase-pentest-skillsQuick reference for all Supabase security audit skills with usage examples and command overview.525skills.sh installs
3yoanbernabeu avatarsupabase-report-compareyoanbernabeu/supabase-pentest-skillsCompare two security audit reports to track remediation progress and identify new vulnerabilities.491skills.sh installs
4prompt-security avatarclawsec-scannerprompt-security/clawsecAutomated vulnerability scanner for agent platforms. Performs dependency scanning (npm audit, pip-audit), multi-database CVE lookup (OSV, NVD, GitHub Advisory),194skills.sh installs
5aradotso avatarautopentestx-automated-pentestingaradotso/security-skillsautopentestx automated pentesting950skills.sh installs
6yoanbernabeu avatarsupabase-audit-realtimeyoanbernabeu/supabase-pentest-skillsTest Supabase Realtime WebSocket channels for unauthorized subscriptions and data exposure.544skills.sh installs