terraform
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides the agent with the ability to execute the
terraformCLI, which includes highly impactful actions such asterraform applyandterraform destroy. These commands can modify or delete critical cloud infrastructure. The inclusion of the-auto-approveflag allows for these destructive actions to occur without manual user confirmation. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and act upon Terraform configuration files (
.tf). - Ingestion points: The agent reads and parses local infrastructure definition files during commands like
init,plan, andapply. - Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts within the infrastructure files are provided.
- Capability inventory: Terraform possesses the capability to execute local shell commands via
local-execprovisioners and interact with remote APIs via various cloud providers. - Sanitization: The skill does not define any sanitization or validation steps for external configuration data beyond the standard
terraform validatecommand.
Audit Metadata