google-sheets
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading data from external Google Sheets, which serves as an ingestion point for untrusted content.
- Ingestion points: The tools
read_rangeandget_spreadsheet(documented inSKILL.md) are used to retrieve values and structural metadata from remote spreadsheets. - Boundary markers: The provided instructions do not specify any delimiters or safety boundaries to separate spreadsheet data from the agent's internal logic.
- Capability inventory: The skill allows the agent to modify spreadsheet values, change structural layouts, and perform file management tasks via referenced Google Drive tools.
- Sanitization: There are no documented steps for validating or sanitizing the data fetched from sheets before it is processed by the agent.
Audit Metadata