terraform-aws-annotated-reference

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to fetch the latest AWS provider version from https://registry.terraform.io/v1/providers/hashicorp/aws, which is the official well-known repository for Terraform providers.
  • [COMMAND_EXECUTION]: The workflow executes terraform init and terraform providers schema -json. The terraform init command downloads the official hashicorp/aws provider binary to the local environment. This is standard behavior for the toolchain used in this skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources, including user-provided resource names, provider versions, and AWS documentation retrieved via MCP tools.
  • Ingestion points: User input (resource name, version), Terraform Registry API responses, and AWS documentation tool outputs.
  • Boundary markers: Not explicitly defined in the prompt interpolation, but the skill uses strict schema validation (jq) and format rules (FR-1 through FR-7) to constrain the output.
  • Capability inventory: The skill can execute shell commands (Bash), read/write files, and interact with specialized AWS knowledge tools.
  • Sanitization: Uses jq to parse and extract structured data from the provider schema, reducing the risk of processing malicious instructions embedded in the schema itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 11:59 PM