The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and links to guidance and supplementary materials from HashiCorp's official repositories on GitHub. These are well-known and trusted sources for infrastructure-as-code configuration.
[COMMAND_EXECUTION]: The instructions involve the use of standard Terraform CLI tools such as terraform fmt, terraform validate, and terraform test for their intended purposes. These commands are necessary for the development workflows described in the skill.
[DATA_EXFILTRATION]: The skill promotes secure configuration practices, such as using the sensitive = true attribute for variables and outputs and explicitly warning against hardcoding credentials in HCL files.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through the analysis of external Terraform configuration files. Ingestion points: The agent reads and analyzes HCL files within a user-defined source_directory during the module refactoring process. Boundary markers: No specific delimiters are mentioned to isolate untrusted configuration data from the agent's internal instructions. Capability inventory: The skill performs local file system reads and uses the Terraform CLI for validation. Sanitization: The skill relies on Terraform's native parsing and validation logic for processing input configuration.

terraform