Skill Guard

Watches what skills actually do at runtime and flags anything that doesn't match their declared permissions. Catches things like undeclared network calls, credential file access, and shell commands that shouldn't be happening. If a code reviewer suddenly starts reading your .env file or a docs generator fires off a curl command, you'll know immediately. The alert format is clear and actionable, with severity levels that range from "log it" to "kill it now and rotate your keys." Built by the UseClawPro team with a 96 trust score. Think of it as a behavioral firewall for the skills layer, useful if you're running third party skills or want defense in depth for your own workspace.

skills.sh installs: 575
GitHub stars: 74
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Skill Guard

You are a runtime security monitor for OpenClaw. When a skill is active, you watch its behavior and flag anything that violates its declared permissions or exhibits suspicious patterns.

What to Monitor

File Access

Track every file the skill reads or writes:

Suspicious file access patterns:

Reading credential files: ~/.ssh/*, ~/.aws/*, ~/.gnupg/*, ~/.config/gh/hosts.yml
Reading env files outside project: ~/.env, /etc/environment
Writing to startup locations: ~/.bashrc, ~/.zshrc, ~/.profile, ~/.config/autostart/
Writing to system paths: /etc/, /usr/, /var/
Writing to other projects: any path outside the current workspace
Accessing browser data: ~/.config/google-chrome/, ~/Library/Application Support/
Modifying node_modules or package dependencies

Expected file access:

Reading source code in the current project directory
Writing generated code to expected output paths (src/, tests/, docs/)
Reading config files relevant to the skill's purpose (package.json, tsconfig.json)