Skill Vetter
Scan a third-party agent skill before you install it in Claude Code, OpenClaw, or another agent setup.
Install
npx skills add https://github.com/app-incubator-xyz/skill-vetter --skill SKILL.mdWhat is this skill?
- Multi-scanner security gate for agent skills
- Triggers on install, add, or review requests for Claude Code and OpenClaw
- Detects malicious code, vulnerabilities, and suspicious patterns
- Designed as a pre-install review step—not post-hoc only
- Applies to skills from any source you paste or point the agent at
Adoption & trust: 34 GitHub stars.
Recommended Skills
Azure Compliancemicrosoft/azure-skills
Openclaw Secure Linux Cloudxixu-me/skills
Entra Agent Idmicrosoft/azure-skills
Firebase Security Rules Auditorfirebase/agent-skills
Firestore Security Rules Auditorfirebase/agent-skills
Skill Vetteruseai-pro/openclaw-skills-security
Journey fit
Installing unreviewed skills is a ship-risk decision; Security is the canonical shelf even though vetting happens whenever you add capabilities. Appsec-style review of skill packages matches the security subphase—malware, suspicious patterns, and vulnerability signals before trust.
SKILL.md
READMESKILL.md - Skill Vetter
Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns. # skill-vetter { "name": "skill-vetter", "description": "Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns." }