The Agent Skills Directory

[SAFE] (SAFE): The skill defines a standard service layer pattern for data management. It focuses on task logic, metadata management (timestamps), and basic validation.
[Indirect Prompt Injection] (LOW): The skill processes external task data. It includes validation logic for required fields and value constraints (e.g., title length, priority categories), which follows best practices for handling untrusted input, although the agent should still be cautious when interpolating user strings into larger prompts.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were found in the provided code snippets.
[Remote Code Execution] (SAFE): The skill provides static templates and does not use any dynamic execution functions like eval() or exec() on external data.

crud-skill