SkillShield – Security-scored directory for AI skills and agent tools

Summary: SkillShield provides a security-scored directory for AI skills by scanning GitHub and GitLab repositories using a four-layer analysis. It delivers trust scores, real-time vulnerability detection, and security badges to help identify safe AI capabilities.

What it does

SkillShield analyzes SKILL.md files through manifest, static code, dependency, and LLM behavioral checks, assigning each skill a 0-100 trust score and detecting vulnerabilities in real time.

Who it's for

It is designed for developers and organizations seeking to discover or validate the security of AI skills and agent tools.

Why it matters

SkillShield addresses the risk of malicious or vulnerable AI skills that could expose data or APIs by providing standardized security assessments.