geospatial-data-pipeline

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection through the processing of untrusted geospatial data.
  • Ingestion points: The scripts scripts/geospatial_processor.ts and scripts/tile_generator.ts use fs.readFileSync to ingest GeoJSON data from local files provided as CLI arguments.
  • Boundary markers: There are no explicit instructions or delimiters in the prompt templates that warn the agent to ignore potentially malicious natural language instructions embedded within GeoJSON properties or metadata fields.
  • Capability inventory: The skill is configured with high-privilege tool access, including Bash with permissions for npm, gdal, and postgres operations.
  • Sanitization: While the scripts use standard JSON.parse to validate JSON structure, there is no content-level sanitization to prevent the agent from being influenced by instructions found inside the data during analysis phases.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:42 PM