The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected in the skill's instructions, metadata, or referenced scripts.
[EXTERNAL_DOWNLOADS]: The skill references several official AWS connectors and tools, such as the awslabs.aurora-dsql-mcp-server (via uvx) and aurora-dsql-loader (from the aws-samples GitHub organization). These are from well-known and trusted sources associated with the platform provider.
[PROMPT_INJECTION]: The instructions do not contain any bypass, override, or role-play injection patterns. Instead, they provide strict guidance on maintaining tenant isolation and safe query construction.
[COMMAND_EXECUTION]: The skill uses standard CLI tools (AWS CLI, psql) for database management tasks, which are appropriate for its stated purpose. It includes clear documentation on how to use these tools securely.
[DATA_EXFILTRATION]: The skill promotes secure data handling by encouraging the use of AWS Secrets Manager and IAM roles, avoiding hardcoded credentials.

dsql