hebrew-survey-builder

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to install the Google Workspace CLI from an official source (github.com/googleworkspace/cli). This is a well-known, legitimate developer tool from a trusted organization.
  • [COMMAND_EXECUTION]: The skill uses the gws CLI to interact with the Google Forms API. These commands are documented for legitimate survey creation purposes and do not involve arbitrary or malicious shell execution.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill includes a dedicated section on privacy and consent (Israel's Privacy Protection Law Amendment 13). It specifically warns the agent to avoid re-identifying anonymous respondents and to disable automatic email collection in Google Workspace environments unless necessary, demonstrating a high degree of privacy awareness.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user intent to select survey templates. While the survey content itself is interpolated into commands, it uses structured JSON payloads via --json flags which mitigates basic command injection risks. The scripts/build_batchupdate_payload.py script further structures this data safely before it reaches the CLI.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. All scripts are local to the skill, and external dependencies are limited to standard, user-installed CLI tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 01:01 AM
Security Audit — agent-trust-hub — hebrew-survey-builder