analyzing-data-dashboard

Warn

Audited by Snyk on Mar 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's tools explicitly auto-download and ingest external GeoJSON map data (see download_dashboard_maps and the note that create_dashboard_cards/update_dashboard_cards/validate_dashboard will automatically download maps) and the project setup allows "网络数据"/web data as data sources, so the agent will read untrusted third‑party content that can affect validation and card-creation behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 12:27 PM
Issues
1