The Agent Skills Directory

[SAFE]: No malicious patterns, hidden commands, or security risks were identified in the skill documentation or code examples.\n- [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters or override agent behavior. The guide promotes structured input handling using Zod, which aids in preventing accidental injection vulnerabilities.\n- [DATA_EXFILTRATION]: No hardcoded credentials or unauthorized network operations were detected. The service logic is designed for dependency injection of authorized clients, ensuring data access is handled through verified framework paths.\n- [REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote code or scripts were identified.\n- [COMMAND_EXECUTION]: The skill does not perform any system command execution or subprocess spawning.\n- [EXTERNAL_DOWNLOADS]: No external downloads are initiated by the skill instructions. References to official Supabase and Next.js libraries are standard for the described tech stack.

service-builder