googlesheets-automation
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at
https://rube.app/mcp. This connects the agent to a remote tool provider, which defines and potentially executes the logic for the Google Sheets interactions. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Google Sheets using tools like
GOOGLESHEETS_BATCH_GETandGOOGLESHEETS_LOOKUP_SPREADSHEET_ROW. - Ingestion points: Data is pulled from spreadsheet cells into the agent's context.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions in the sheet data.
- Capability inventory: The skill includes powerful write and delete capabilities, such as
GOOGLESHEETS_BATCH_UPDATEandGOOGLESHEETS_DELETE_DIMENSION. - Sanitization: No sanitization or validation of the sheet content is mentioned before it is processed or used in further tool calls.
- [DYNAMIC_EXECUTION]: The skill utilizes
RUBE_SEARCH_TOOLSto dynamically fetch tool schemas at runtime. This means the exact behavior and interface of the tools are not statically defined in the skill and can be modified by the remote MCP server provider.
Audit Metadata