recipe-generate-report-from-sheet
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is authored by 'googleworkspace' and utilizes the 'gws' CLI tool, which is a verified resource for this vendor. All operations described in the recipe are routine productivity tasks within the Google Workspace environment.
- [COMMAND_EXECUTION]: The recipe steps involve executing commands via the 'gws' binary to interact with Sheets, Docs, and Drive. As these commands are part of the vendor-provided toolset for the skill, they are considered safe for the intended automation use case.
- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it processes content from external Google Sheets.
- Ingestion points: Data is read from a Google Sheet (SKILL.md, Step 1).
- Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions potentially contained within the spreadsheet data.
- Capability inventory: The skill allows for writing to documents and modifying file permissions in Google Drive.
- Sanitization: No sanitization or validation of the ingested spreadsheet data is mentioned in the recipe.
Audit Metadata