The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides installation instructions that reference official and well-known sources, including the terragrunt binary from the official website https://terragrunt.gruntwork.io/ and installation via the brew package manager. These are standard and legitimate sources for the infrastructure tool described.\n- [COMMAND_EXECUTION]: The instructions enable the agent to execute standard CLI commands for the tool, such as terragrunt plan, terragrunt apply, and terragrunt run-all. These commands are essential for the skill's stated purpose of managing infrastructure and do not involve unauthorized privilege escalation or persistence mechanisms.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external configuration files (.hcl) which creates an ingestion surface for indirect prompt injection.\n
Ingestion points: The agent is instructed to read local configuration files using functions like read_terragrunt_config() and find_in_parent_folders().\n
Boundary markers: No specific boundary markers or instruction-ignoring delimiters are defined for the configuration content in the provided examples.\n
Capability inventory: The skill utilizes command execution for infrastructure deployment (terragrunt apply).\n
Sanitization: No explicit sanitization of the configuration file content is mentioned. However, as this is the primary function of an Infrastructure-as-Code expert skill, the risk is assessed as safe within this specific context.

terragrunt