terraform-iac

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the official hashicorp/terraform-mcp-server image from Docker Hub. As HashiCorp is a well-known and established technology provider, this external dependency is considered safe.
  • [CREDENTIALS_SAFE]: The instructions correctly advocate against hardcoding secrets, recommending the use of environment variables (TFE_TOKEN) for authentication to HCP Terraform.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests documentation and module metadata from the Terraform Registry, creating a theoretical surface for indirect prompt injection.
  • Ingestion points: External data is fetched via get_provider_details, get_module_details, and get_policy_details from the Terraform Registry.
  • Boundary markers: No specific delimiters are defined in the skill instructions to separate external content from instructions.
  • Capability inventory: The skill facilitates workspace management, variable set creation, and execution of Terraform runs via the MCP server.
  • Sanitization: No explicit sanitization or filtering logic is defined for the fetched documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 10:47 AM
Security Audit — agent-trust-hub — terraform-iac