The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or reference materials.\n- [PROMPT_INJECTION]: The skill contains technical instructions for SwiftUI code review and refactoring. No attempts to override agent behavior, bypass safety filters, or extract system prompts were found.\n- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected. The profiling reference specifically warns against logging sensitive values in signpost messages.\n- [REMOTE_CODE_EXECUTION]: The skill provides standard macOS development CLI commands (e.g., xctrace, simctl) for local profiling by the user. It does not download or execute remote scripts.\n- [COMMAND_EXECUTION]: All commands mentioned are standard development tools and are intended for manual execution or guided profiling within the developer's environment.\n- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or other sensitive credentials were found in the skill metadata or body.

swiftui-performance