sweetviz
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Prompt Injection] (LOW): The skill identifies a surface for indirect prompt injection through data ingestion. • Ingestion points: pd.read_csv('data.csv') in README.md. • Boundary markers: Absent. • Capability inventory: report.show_html (local file writing). • Sanitization: Absent.
- [External Downloads] (SAFE): The skill suggests installing 'sweetviz' via pip. This is a well-established and trusted library in the data science community.
Audit Metadata