13 results for tag "skill-vetter"
Security-first skills for the OpenClaw ecosystem providing skill auditing (typosquatting, permissions, prompt injection detection) and environment setup auditing (credential leaks, unsafe defaults, missing sandbox).
Validates and scores open-source skills for security, performance, and best practices in the Claude Code ecosystem
A security auditor skill that vets SKILL.md files before installation by checking for typosquatting, permission abuse, prompt injection, supply chain attacks, and data exfiltration, returning a SAFE/SUSPICIOUS/DANGEROUS/BLOCK verdict.