Terraform Plan Analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Terraform plan output, which is a surface for untrusted data that could potentially contain adversarial instructions.
- Ingestion points: Terraform plan JSON output as mentioned in the description.
- Boundary markers: No delimiters or instructions for the agent to ignore embedded content are specified.
- Capability inventory: Uses the
terraformCLI to generate JSON and interacts with Infracost and OPA APIs. - Sanitization: The documentation does not describe any sanitization or validation of the plan data before analysis.
Audit Metadata