The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts scripts/agent.py and scripts/process.py utilize the Python subprocess module to execute gcloud CLI commands. These commands are essential for auditing and applying organization policies as described in the skill's purpose. The implementation uses list-based arguments rather than shell strings, which follows security best practices to prevent command injection.
[INDIRECT_PROMPT_INJECTION]: The skill processes output from GCP APIs via gcloud. While this represents a data ingestion surface, the risk is minimal as the source is a trusted administrative tool and the data is primarily used for reporting and generating local Terraform configurations.

implementing-gcp-organization-policy-constraints