weather-search
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches geographical coordinates from Nominatim (OpenStreetMap) and weather/air quality forecasts from Open-Meteo. These are well-known, public, and reputable services used for their intended purpose.
- [COMMAND_EXECUTION]: All filesystem operations are restricted to writing the final Markdown report to a user-defined or default directory. The skill uses standard Python libraries for path manipulation and directory creation, ensuring behavior remains within expected bounds.
- [PROMPT_INJECTION]: The skill architecture includes a surface for indirect prompt injection because it processes data from external APIs. However, this is categorized as safe because the ingested data is primarily numeric weather statistics, and the agent's instructions are limited to formatting advice in a Markdown table. There is no evidence of instructions that attempt to bypass safety filters or override agent identity.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found. The external services utilized in the skill do not require authentication for the demonstrated use case.
Audit Metadata