skills/terminalskills/skills/leaflet/Gen Agent Trust Hub

leaflet

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions reference fetching map tiles from OpenStreetMap, a standard and well-known open-source geospatial service.
  • [COMMAND_EXECUTION]: Provides instructions to install standard mapping libraries including leaflet and react-leaflet using npm install.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines components that render map markers and popups from external data sources, which represents a common vulnerability surface.
  • Ingestion points: The stores and zones data structures processed in the React components in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are used to distinguish map data from potential prompt content in popups.
  • Capability inventory: Generates UI code and performs package management via npm.
  • Sanitization: Data properties are interpolated directly into popup template strings without visible sanitization in the provided snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:56 AM
Security Audit — agent-trust-hub — leaflet