The Agent Skills Directory

[SAFE]: The skill serves as a reference for the official Port Terraform provider. All code examples are standard HCL and do not contain malicious payloads.
[CREDENTIALS_UNSAFE]: The skill correctly identifies the risks associated with API credentials. It includes explicit warnings against hardcoding client IDs and secrets in configuration files, recommending environment variables as a secure alternative.
[DATA_EXFILTRATION]: The skill references official service endpoints (api.port.io) and repositories. These are legitimate resources required for the functionality of the provider.
[PROMPT_INJECTION]: The skill facilitates the generation of Terraform HCL from user requirements. It manages the risk of indirect prompt injection by documenting a lifecycle that requires human review through commands like terraform plan before any changes are applied to the live environment.

port-terraform