cesiumjs-entities

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for loading and rendering geospatial data from external sources, which is a potential surface for indirect prompt injection if the ingested data is malicious.
  • Ingestion points: The skill describes methods for loading external data files using GeoJsonDataSource.load(), KmlDataSource.load(), CzmlDataSource.load(), and GpxDataSource.load().
  • Boundary markers: The instructions do not include boundary markers or warnings to the agent to ignore instructions embedded within these data files.
  • Capability inventory: The skill allows the agent to visualize complex geospatial data and render HTML in entity descriptions within the CesiumJS viewer UI.
  • Sanitization: The documentation does not specify sanitization procedures for data processed from these external formats.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:29 PM
Security Audit — agent-trust-hub — cesiumjs-entities