The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to facilitate the use of the gdrv command-line utility for Google Drive operations, including file management and administrative tasks.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes untrusted data from external sources. Ingestion points: The agent reads data via gdrv docs read, gdrv sheets values get, and gdrv files list. Boundary markers: There are no explicit markers or instructions to ignore embedded commands within the processed data. Capability inventory: The tool has broad capabilities including file deletion (gdrv files delete), administrative user deletion (gdrv admin users delete), and permission modification (gdrv permissions create). Sanitization: There is no evidence of sanitization or validation performed on the retrieved data before it enters the agent context.
[CREDENTIALS_UNSAFE]: The documentation references sensitive file paths such as service-account-key.json and uses environment variable placeholders (GDRV_CLIENT_ID, GDRV_CLIENT_SECRET) for authentication. It also includes an example command with a hardcoded temporary password.

gdrv-cli