The Agent Skills Directory

[SAFE]: The skill provides educational content and best practice recommendations for infrastructure-as-code development.
The documentation covers project structure, naming conventions, and version management based on community-recognized standards.
Security recommendations include using managed secret stores, enabling encryption, and implementing least-privilege principles.
[COMMAND_EXECUTION]: The skill suggests the use of standard open-source security scanning tools for static analysis.
Evidence: Instructions provide example commands 'trivy config .' and 'checkov -d .' to be used for identifying vulnerabilities in configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided Terraform code, which represents an ingestion surface for untrusted data.
Ingestion points: Terraform configuration files ('.tf') provided by the user for review or refactoring tasks.
Boundary markers: No specific delimitation instructions or 'ignore' blocks are provided for the input code.
Capability inventory: The skill identifies resources and structure but does not include scripts with subprocess calls or network operations; it recommends running external security CLIs.
Sanitization: No sanitization logic is present as the skill operates as a set of prompt instructions.

terraform-skill