gws-drive
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gwscommand-line tool to perform administrative and management tasks on Google Drive resources. - [EXTERNAL_DOWNLOADS]: Fetches file content, metadata, and exported documents from the well-known Google Workspace Drive API.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external, untrusted sources (Google Drive files and comments) which could contain malicious instructions.
- Ingestion points: External data enters the agent context through
files.get(content),files.download,files.export,comments.list, andreplies.listoperations defined inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to treat data retrieved from Drive as untrusted.
- Capability inventory: The agent has the ability to execute shell commands via
gws, create/update files, and modify file/drive permissions. - Sanitization: There is no evidence of sanitization or validation of the retrieved content before it is processed by the agent.
Audit Metadata