Shield + Dino

What problem does it solve?

This Skill detects and analyzes potentially malicious AI skills, identifying prompts and code patterns that threaten security and integrity.

Core Features & Use Cases

• Threat Detection: Identifies prompt injections, dangerous system commands, code execution vulnerabilities, and data exfiltration in AI skill files.
• Risk Scoring: Assigns severity levels and calculates overall risk scores for AI skills.
• Use Case: Before deploying third-party AI skills, use this Skill to vet for security risks such as prompt hijacking or malicious scripts.

Quick Start

Use the Shield + Dino skill to scan a skill file or directory for security vulnerabilities with a single command.