questionnaire
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely offline. The generated HTML questionnaire includes a strict Content Security Policy (CSP) that disables network access (
connect-src 'none') and prevents external resource loading. All data is stored locally in the user's browserlocalStorageand only leaves the machine when the user explicitly copies the markdown output back to the agent session.- [COMMAND_EXECUTION]: The skill includes a Python build script (scripts/build.py) used to generate the HTML questionnaire. This script performs basic validation on the input JSON and performs simple string replacement to embed the configuration into a static template. It does not perform any dangerous system operations, privilege escalation, or remote downloads.- [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The workflow is designed for privacy, requiring manual user action to share results. The developer guidelines explicitly mention telling the user when content is personal and that answers never leave their machine autonomously.
Audit Metadata