weather
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in this skill.
- [EXTERNAL_DOWNLOADS]: The skill references fetching data from well-known services including wttr.in and Open-Meteo. These references are consistent with the skill's primary function and target established public weather data providers.
- [PROMPT_INJECTION]: The skill describes a workflow that involves ingesting untrusted data from external weather APIs. This creates a surface for indirect prompt injection if the external source provides malicious content designed to influence the agent's behavior. * Ingestion points: Weather API response fields (e.g., weather descriptions, alerts) as documented in SKILL.md. * Boundary markers: Not specified in the current instructions. * Capability inventory: The skill is scoped to weather retrieval functions (get_weather, get_weather_forecast) and alerting. * Sanitization: No explicit sanitization or validation of external strings is described.
Audit Metadata