The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/agent.py executes external security scanning binaries using subprocess.run with argument lists. This is a secure implementation that prevents shell injection attacks.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Terraform files and plans, creating an ingestion surface for untrusted data. However, the scope is limited to local security analysis, and the script handles the data as structured JSON or text for reporting purposes.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing well-known, industry-standard security tools from trusted registries such as PyPI and Homebrew.

auditing-terraform-infrastructure-for-security