skills/atvari-eu/nix-skills/terranix/Gen Agent Trust Hub

terranix

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and convert external configuration files, which presents a surface for processing untrusted data.
  • Ingestion points: The agent reads user-provided HCL (.tf) and Nix (.nix) files to perform migration tasks and fix evaluation errors.
  • Boundary markers: No specific delimiters or boundary markers are instructed for use when the agent interpolates or processes content from these input files.
  • Capability inventory: The skill utilizes shell commands such as nix-instantiate, terranix, and tofu which can trigger local file system access and network operations for provider downloads.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the input files before processing them through evaluation tools.
  • [EXTERNAL_DOWNLOADS]: The skill references and utilizes external code and dependencies from established ecosystem sources.
  • Evidence: The skill recommends using the official Terranix flake (github:terranix/terranix) and the standard Nix package repository (nixpkgs) for its core functionality.
  • Evidence: The skill includes instructions for tofu init, which involves downloading required infrastructure providers from well-known registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 02:31 AM