skills/mukul975/anthropic-cybersecurity-skills/implementing-google-workspace-admin-security/Gen Agent Trust Hub
implementing-google-workspace-admin-security
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation in SKILL.md provides shell examples and commands for using the 'gam' (Google Apps Manager) CLI tool to configure security settings and perform audits. These commands are standard administrative actions for the Google Workspace platform.
- [INDIRECT_PROMPT_INJECTION]: The Python script 'scripts/agent.py' interacts with Google Workspace APIs to retrieve user profiles and login activity logs. This data is used to generate security reports, which represents a low-risk ingestion of external data.
- Ingestion points: Google Workspace Directory API (users().list) and Reports API (activities().list) in 'scripts/agent.py'.
- Boundary markers: None; the data is used for status verification and reporting.
- Capability inventory: The script is limited to read-only API requests (GET/List) for auditing purposes. Write operations are documented as separate manual commands in SKILL.md.
- Sanitization: None; the script generates plain text and JSON audit summaries.
- [EXTERNAL_DOWNLOADS]: The skill references official documentation from Google and the CIS Benchmark for security hardening. The Python script depends on well-known, official libraries for Google Cloud and Workspace API interaction.
Audit Metadata