Agent Skills

SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.

Filters

Skill Vetter — Multi-scanner Security Gate

skill-vetter

Runs multiple static and heuristic scanners against incoming skills before installation; detects prompt injection, secrets, and known malicious patterns and rep

securityvettingscanner

7 triggers

Anthropic Security Basics

skillshub

Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.

securityanthropicclaude

6 triggers