The Agent Skills Directory

[SAFE]: The skill provides educational templates for common backend tasks such as API design, database access, and error handling. No malicious instructions or patterns were identified.
[CREDENTIALS_UNSAFE]: No hardcoded secrets were found. The code snippets correctly demonstrate the use of environment variables (e.g., process.env.JWT_SECRET) for managing sensitive configuration.
[PROMPT_INJECTION]: There are no attempts to override agent behavior, bypass safety filters, or extract system instructions.
[EXTERNAL_DOWNLOADS]: The skill does not perform any remote code downloads or execution. All provided code is local and static.
[DATA_EXFILTRATION]: No patterns associated with data exfiltration or unauthorized network access were detected. Network examples (e.g., Redis, Supabase) are standard backend integrations.

backend-patterns