The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses parameterized SQL queries (e.g., WHERE g.id = $1) across all examples, which is a standard security best practice for preventing SQL injection attacks.
[CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill correctly recommends using environment variables (process.env.DATABASE_URL) for database connection strings and provides instructions for production SSL configuration.
[DATA_EXFILTRATION]: No unauthorized network operations or exfiltration patterns detected. The code snippets focus entirely on local database interactions and standard application logic.
[DYNAMIC_EXECUTION]: No usage of unsafe execution functions like eval() or exec(). Database operations use the standard pg pool library in a safe manner.
[PROMPT_INJECTION]: The instructions are strictly technical and professional, containing no attempts to override system prompts or bypass safety guidelines.

game-database