writing-streamlit-apps
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides defensive programming instructions, specifically warning against interpolating unvalidated user input into database queries to prevent HogQL injection.
- [SAFE]: The execution environment is described as a restricted, unprivileged sandbox with a pre-defined set of standard data science and web libraries, with explicit statements that arbitrary package installation via pip is disabled.
- [SAFE]: Data access is handled through a pre-authenticated bridge module (
posthog_apps.query()), which prevents the need for hardcoded credentials or manual secret management within the application source code.
Audit Metadata