iac-planner

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the Bash tool to execute terraform plan on HCL code that is dynamically generated according to user requirements.
  • [EXTERNAL_DOWNLOADS]: Terraform operations routinely download provider plugins and modules from the HashiCorp Terraform Registry to satisfy configuration requirements.
  • [PROMPT_INJECTION]: The skill processes untrusted user input to generate infrastructure-as-code, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided parameters for infrastructure provisioning (e.g., Cloud provider, instance size, regions) as described in SKILL.md instructions.
  • Boundary markers: Absent. The skill does not define clear delimiters or "ignore" instructions for external content.
  • Capability inventory: Access to Bash (shell execution), Write (file system modification), and Read (file system access).
  • Sanitization: Absent. There are no explicit steps to validate or sanitize user input before it is interpolated into the generated Terraform files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:43 AM
Security Audit — agent-trust-hub — iac-planner