gis-file-and-crs

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (GeoJSON, KML, CSV, and coordinate text) through the open_gis_file and convert_coordinates tools. Instructions found in this data could potentially influence agent behavior.
  • Ingestion points: open_gis_file accepts files, public URLs, or pasted text; convert_coordinates accepts text input.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content in the GIS data.
  • Capability inventory: The agent can call external tools to read files and convert coordinates.
  • Sanitization: No explicit sanitization or validation of the content within the GIS files is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill requires a connection to a Model Context Protocol (MCP) server at https://mcp.terra-lab.ai/mcp. This is a vendor-owned service used to provide the skill's core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 09:07 AM