The Agent Skills Directory

[SAFE] (SAFE): The skill provides a structured approach for organizing SwiftUI views. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were identified. All provided code examples are standard SwiftUI patterns.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process external code files (SwiftUI views) for refactoring. While this creates a surface for indirect prompt injection, the skill itself lacks any dangerous capabilities—such as file writing, network access, or command execution—that could be leveraged by an attacker. The risk is limited to the agent producing sub-optimal or intentionally styled code if the input source is adversarial.

swiftui-view-refactor