The Agent Skills Directory

[COMMAND_EXECUTION]: The skill autonomously executes shell commands to perform Terraform operations (init, plan, apply, destroy), run security scanners (tfsec, Checkov), and interact with provider-specific CLI tools. This is a high-privilege capability required for the skill's intended infrastructure management functions.\n- [EXTERNAL_DOWNLOADS]: The skill performs standard Terraform operations that involve downloading provider binaries and modules from official registries. These operations are essential for infrastructure management and target well-known, trusted services.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a vulnerability surface where malicious instructions could be embedded.\n
Ingestion points: Data enters the agent's context through WebSearch results during documentation research, analysis of error logs and diagnostic information from cloud providers, and the review of existing infrastructure configurations.\n
Boundary markers: There are no specific instructions or delimiters defining boundaries to ignore instructions embedded within the processed external data.\n
Capability inventory: The skill combines data ingestion with the ability to write and edit files, as well as execute shell commands.\n
Sanitization: No explicit sanitization or validation protocols are defined for handling external content before it is interpolated into the agent's reasoning or output.

terraform-tasks