The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Terraform CLI to execute infrastructure commands such as fmt, validate, plan, and apply. These actions are restricted to non-production environments unless manual approval is granted.
[INDIRECT_PROMPT_INJECTION]: The skill parses external configuration files (.tf, .tfvars) and command outputs, which creates a potential surface for indirect instructions if those files contain malicious comments or metadata.
[SAFE]: The instructions explicitly implement defensive practices, such as warning against hardcoding credentials in state or plan files and protecting production environments from autonomous mutations.

infra-terraform