skills/arcanexis/alice-single/weather/Gen Agent Trust Hub

weather

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The script weather_tool.py performs network requests to api.open-meteo.com and geocoding-api.open-meteo.com. These are external domains not included in the pre-approved trust whitelist.
  • [INDIRECT_PROMPT_INJECTION] (INFO): The skill displays content directly from an external API, creating a surface for indirect prompt injection. 1. Ingestion points: JSON responses from the Open-Meteo API in weather_tool.py. 2. Boundary markers: None present. 3. Capability inventory: Limited to console output via print() statements. No file-write, command-execution, or network-write capabilities identified. 4. Sanitization: The tool parses structured JSON but does not sanitize the string values (e.g., city names, weather descriptions) before outputting them to the agent context.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:31 AM