recipe-generate-report-from-sheet

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Google Workspace CLI tools to automate document workflows.\n- [COMMAND_EXECUTION]: Uses gws tools to read from spreadsheets and create/share documents.\n- [PROMPT_INJECTION]: The skill reads external data from Google Sheets, creating a surface for indirect prompt injection where malicious instructions in a spreadsheet could influence agent behavior.\n
  • Ingestion points: Spreadsheet data is retrieved in Step 1 using gws sheets +read in SKILL.md.\n
  • Boundary markers: None present in the recipe to distinguish between data and instructions.\n
  • Capability inventory: The skill has the ability to share files via gws drive permissions create in SKILL.md.\n
  • Sanitization: No validation or filtering is applied to the data retrieved from the spreadsheet.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM