recipe-generate-report-from-sheet

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'gws' command-line tool, a vendor-specific utility for Google Workspace, to perform operations such as reading spreadsheets, creating documents, and modifying file permissions.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading content from external Google Sheets via the gws sheets +read command.
  • Ingestion points: Data is pulled from spreadsheet ranges (e.g., 'Sales!A1:D') into the agent's context.
  • Boundary markers: None identified in the provided instructions to delimit sheet data from the agent's instructions.
  • Capability inventory: The skill can write to Google Docs and modify Google Drive permissions to share files.
  • Sanitization: No specific sanitization or validation of the ingested sheet data is mentioned before it is interpolated into the generated report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:12 AM