The Agent Skills Directory

[PROMPT_INJECTION]: The instructions focus strictly on Terraform and Infrastructure-as-Code best practices. No attempts to bypass system prompts or influence the AI's core behavior were found.
[CREDENTIALS_UNSAFE]: The skill includes explicit security guidelines to avoid hardcoding secrets and to use the sensitive = true attribute for variables. No hardcoded credentials were found in the skill source.
[EXTERNAL_DOWNLOADS]: No unauthorized or suspicious external downloads were identified. The skill references well-known industry security tools such as tflint, trivy, and checkov as part of a recommended testing workflow.
[DATA_EXFILTRATION]: The skill does not contain instructions to transmit data to external servers or access sensitive local files like SSH keys or environment configurations.
[COMMAND_EXECUTION]: The skill recommends standard Terraform and OpenTofu CLI commands for formatting, validation, and security scanning. These commands are typical for the described domain and are intended for use in a developer environment.

ia-terraform