The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/agent.py script utilizes subprocess.run() to execute the gam (Google Apps Manager) CLI tool. This is the primary method for retrieving Google Workspace configurations and is implemented using secure practices, such as list-based execution without shell invocation.
[INDIRECT_PROMPT_INJECTION]: The skill processes external JSON data to generate security audit reports, representing a standard ingestion surface.
Ingestion points: The scripts scripts/agent.py and scripts/process.py read user-provided JSON files for configuration, DMARC analysis, and incident logs.
Boundary markers: Not used in the parsing logic.
Capability inventory: The skill has the ability to execute the gam CLI tool and write output to the local file system.
Sanitization: Data is parsed using the standard json module, providing basic structural validation, although specific field content is not validated against a strict schema.
[EXTERNAL_DOWNLOADS]: The documentation references official Google Workspace support documentation, the Advanced Protection Program, and the open-source GAM administrative tool. These are recognized and standard resources for the cybersecurity domain.
[SAFE]: The skill's operations, scripts, and documentation are entirely consistent with its stated objective of hardening Google Workspace environments. No malicious patterns or significant security risks were identified.

implementing-google-workspace-phishing-protection