gws-drive
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gwscommand-line tool to perform operations on Google Drive resources. - [EXTERNAL_DOWNLOADS]: References official Google Workspace documentation for API methods and usage guidelines.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted content from Google Drive (files, comments, and metadata).
- Ingestion points: Methods like
files.get,files.list, andcomments.listinSKILL.mdbring external data into the agent's context. - Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate untrusted content from the agent's instructions.
- Capability inventory: The skill has extensive capabilities including creating, updating, and deleting files, as well as managing sharing permissions.
- Sanitization: No evidence of sanitization or content validation for data retrieved from Google Drive.
Audit Metadata