Skills
skills/donngi/agent-skills/terraform-aws-annotated-blueprint/Gen Agent Trust Hub

terraform-aws-annotated-blueprint

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill runs terraform init and terraform providers schema to extract resource definitions from local providers.
  • [COMMAND_EXECUTION]: Executes the included shell script lib/validate_template.sh to perform automated formatting checks on generated HCL files.
  • [EXTERNAL_DOWNLOADS]: Communicates with the official Terraform Registry API (registry.terraform.io) to identify the most recent AWS provider version.
  • [PROMPT_INJECTION]: The skill processes untrusted user input to define infrastructure requirements, representing an indirect prompt injection surface. Evidence: 1. Ingestion point: {概要} variable in SKILL.md. 2. Boundary markers: Not present. 3. Capability inventory: Execution of terraform, jq, and bash via SKILL.md. 4. Sanitization: Not observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 02:15 AM