Skill Vetter

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...

This skill is a coherent, conservative vetting checklist and safe as an instruction-only helper. Before using it, ensure the agent has only the minimum permissions needed to fetch and inspect candidate skill repositories (network access and read access to the skill package). Remember: vetting a skill via these checks does not sandbox or prevent a vetted skill from later performing malicious actions at runtime — for higher-risk skills manually review code, prefer running them in isolated sandboxes, verify releases/tags on authoritative repos, and require human approval for any skill that requests credentials or system access.

Type: OpenClaw Skill Name: nidhov01-skill-vetter Version: 1.0.0 The 'skill-vetter' bundle is a security-oriented tool designed to provide a vetting protocol for AI agents to evaluate other skills before installation. The SKILL.md file contains instructions, checklists, and template reports focused on identifying red flags such as data exfiltration, unauthorized credential access, and obfuscated code, with no evidence of malicious intent or harmful commands.