gws
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@googleworkspace/clipackage globally via npm. - [COMMAND_EXECUTION]: The skill uses the
gwscommand-line tool to read, write, and manage Google Workspace resources, often involving complex JSON parameters and shell execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external documents which could contain malicious instructions.
- Ingestion points: Operations like
gws sheets +read(references/sheets.md) andgws docs get(references/docs.md) fetch content from user-controlled files. - Boundary markers: The instructions in SKILL.md recommend user confirmation for write/delete actions and highlight the use of the
--sanitizeflag with Model Armor. - Capability inventory: The skill possesses extensive capabilities including file deletion (references/drive.md), data updates (references/sheets.md), and task management (references/tasks.md).
- Sanitization: The CLI tool includes a dedicated
--sanitizeflag to filter responses through Model Armor.
Audit Metadata