The Agent Skills Directory

[SAFE]: The skill is purely instructional and provides legitimate architectural guidance for software development. No malicious code or security threats were detected.- [CREDENTIALS_UNSAFE]: Example code for database connections correctly uses environment variables rather than hardcoding secrets, and the skill includes a self-verification check to ensure no passwords or API keys are committed to source control.- [PROMPT_INJECTION]: The content defines a technical persona focused on backend architecture without attempting to bypass safety filters or redefine the agent's core instructions.- [DATA_EXFILTRATION]: No network exfiltration or unauthorized file access patterns were found in the instructions or code examples.

backend-architect