terraform-specialist
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists exclusively of markdown instructions defining a persona. There are no executable scripts, configuration files for package managers, or shell commands provided.\n- [PROMPT_INJECTION] (SAFE): The instructions do not contain any patterns intended to bypass AI safety filters, extract system prompts, or override agent constraints. The language is purely instructional and context-specific.\n- [DATA_EXFILTRATION] (SAFE): There are no network-capable commands (e.g., curl, wget) or references to sensitive local file paths (e.g., ~/.ssh). Mentions of remote state backends like S3 or Azure Storage are standard for Terraform and do not involve data exfiltration logic.\n- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not define or reference any external packages, dependencies, or remote scripts to be downloaded at runtime.
Audit Metadata