gws-sheets-read
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwscommand-line tool to interface with Google Workspace APIs. This is a standard functional requirement for the skill. - [INDIRECT_PROMPT_INJECTION]: The skill reads external content from Google Sheets, which could contain malicious prompts designed to bypass agent constraints or redirect behavior.
- Ingestion points: Data retrieved from specified ranges within a Google Spreadsheet via the
gws sheets +readcommand. - Boundary markers: The instructions do not specify any delimiters or safety markers to wrap the ingested spreadsheet data when it is presented to the agent.
- Capability inventory: The skill utilizes the
gwsbinary, which is part of a larger suite of tools for interacting with Google Workspace. - Sanitization: No validation or sanitization is performed on the data fetched from the spreadsheet before processing.
Audit Metadata