The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains purely instructional content for infrastructure development. No attempts to override system prompts, bypass safety filters, or exfiltrate internal instructions were detected.
[Data Exposure & Exfiltration] (SAFE): The examples use placeholders and variables for cloud configuration. No hardcoded secrets, API keys, or unauthorized access to sensitive local files (like SSH keys or AWS credentials) are present.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The provider configuration references the official HashiCorp AWS provider. While the workflow includes terraform init, which downloads providers, this is the intended and standard behavior for the tool.
[Command Execution] (SAFE): The workflow section documents standard Terraform CLI commands (init, plan, apply). These are restricted to the primary purpose of the skill and do not involve arbitrary or hidden shell execution.
[Obfuscation] (SAFE): No encoded strings, zero-width characters, or hidden payloads were found in the skill content.
[Persistence Mechanisms] (SAFE): No commands attempt to modify system startup files, cron jobs, or shell profiles.

terraform