recipe-generate-report-from-sheet
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external Google Sheets, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads data using the
gws sheets +readcommand inSKILL.md. - Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore embedded commands within the spreadsheet content.
- Capability inventory: The skill has the ability to create documents (
gws docs documents create), write content (gws docs +write), and modify sharing permissions (gws drive permissions create). - Sanitization: There is no evidence of sanitization or validation of the data retrieved from the spreadsheet before it is used in subsequent operations.
- [COMMAND_EXECUTION]: The skill requires the
gwsbinary and executes several subcommands to interact with Google Workspace services. While these are legitimate tools for the skill's purpose, they represent the capability to modify and share cloud-hosted files based on the processed data.
Audit Metadata