gws-drive
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the Google Drive API by executing the
gwscommand-line binary. It supports a wide range of methods includingfiles.create,files.delete, andpermissions.updateas part of its core functionality.- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it is designed to read and process untrusted external data from Google Drive. - Ingestion points: Data is ingested through API methods such as
files.get(withalt=media),files.download,comments.list, andreplies.listas defined inSKILL.md. - Boundary markers: This file does not specify explicit boundary markers or 'ignore' instructions for the data it retrieves, although it references global security rules in
../gws-shared/SKILL.md. - Capability inventory: The skill has extensive capabilities to modify Drive resources, including the ability to change file permissions and delete revisions.
- Sanitization: No input sanitization or validation protocols are described for the content retrieved from the Drive API within the provided instructions.
Audit Metadata