The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The workspace_audit.py and gws_doctor.py scripts ingest untrusted configuration data in JSON format from the local file system. While this represents a data ingestion surface, the scripts perform read-only analysis and report generation without dangerous capabilities like network operations, file writing, or subprocess execution that could be exploited via malicious data content.
[EXTERNAL_DOWNLOADS]: The auth_setup_guide.py script and documentation recommend the installation of official Google authentication libraries (google-auth, google-auth-oauthlib, google-api-python-client). These originate from a well-known, trusted organization and are intended for legitimate API interaction as part of the skill's primary purpose.

google-workspace-cli