The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill uses a shell script scripts/init-terraform.sh to dynamically generate Terraform configuration files (terraform/main.tf) based on user-supplied project and region arguments.
[COMMAND_EXECUTION]: The skill is configured with access to Bash(terraform:*) and Bash(gcloud:*) tools to perform deployment, validation, and infrastructure provisioning tasks as described in the documentation and examples.
[INDIRECT_PROMPT_INJECTION]: The skill processes Genkit application configurations to generate infrastructure modules, creating a surface where malicious instructions in the application code could influence the agent's actions during the infrastructure setup.
Ingestion points: The skill reads Genkit application layouts and Terraform structures using Read, Glob, and Grep tools.
Boundary markers: No specific delimiters or instructions to ignore embedded content were identified in the prompt logic.
Capability inventory: The skill has extensive file-writing capabilities and execution rights for infrastructure management CLI tools.
Sanitization: No explicit sanitization or validation logic for the input configuration data is implemented before it is used in the module generation process.

genkit-infra-expert