The Agent Skills Directory

[SAFE]: The skill consists of instructional content regarding infrastructure-as-code best practices and does not contain executable malicious code or deceptive instructions.
[COMMAND_EXECUTION]: The skill mentions standard industry tools such as terraform, tflint, trivy, and checkov. These references are strictly instructional for development and security auditing workflows.
[CREDENTIALS_UNSAFE]: The content explicitly encourages secure practices, such as using AWS Secrets Manager and marking sensitive variables, while warning against hardcoding secrets.
[PROMPT_INJECTION]: No patterns of instruction overrides, safety filter bypasses, or system prompt extraction were found.
[DATA_EXFILTRATION]: There are no commands or scripts that access sensitive local files or attempt to transmit data to external domains.

terraform-skill