google-apps-script
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates and patterns for processing data from external sources such as Google Sheets (
SpreadsheetApp), Google Forms (onFormSubmit), and external APIs (UrlFetchApp). While these are standard features for automation, they represent an entry point for untrusted data that could potentially be used for indirect prompt injection if the agent processes the content without further sanitization. The provided templates include basic filtering and error handling, but do not implement specific delimiters for large language model safety. - Ingestion points:
assets/spreadsheet-automation-template.js(reads fromSpreadsheetApp),references/patterns.md(reads frome.valuesin form submissions). - Boundary markers: None present in the provided templates.
- Capability inventory: The templates have capabilities to send emails (
MailApp.sendEmail), write to spreadsheets (SpreadsheetApp.setValues), and perform HTTP requests (UrlFetchApp). - Sanitization: The skill provides a Python validation script (
scripts/validators.py) for data structure and format validation, but no NLP-specific sanitization. - [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/validators.py) intended for local validation of spreadsheet IDs and A1 notations. The script uses standard libraries and does not execute arbitrary shell commands or access sensitive system paths.
Audit Metadata