Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims: fetches weather and uses Sonos locally for a morning wake-up routine.
Install only if you are comfortable with the skill sending your configured location or coordinates to Open-Meteo and controlling the named Sonos speaker. Review any cron schedule you add, since recurring playback can be disruptive if configured incorrectly.
The stated purpose sounds like a simple morning automation, but the documented behavior includes external network lookups and local speaker control that are not transparently declared as permissions. This mismatch can mislead users about the operational scope of the skill and make risky side effects easier to hide inside an apparently harmless routine.
Referenced artifact was not completely inspected
bun scripts/morning-wakeup.ts --location "Shanghai" --speaker "Bedroom"
The skill documentation describes behavior that requires network access to fetch weather and likely local command execution to control Sonos, but it declares no explicit tool scope or permissions. This creates a trust and review gap: users or orchestration systems may authorize or run a skill with capabilities that are broader than what its manifest transparently states.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
current: "temperature_2m,weather_code",
temperature_unit: tempUnit, timezone: "auto", forecast_days: "1",
});
const url = `https://api.open-meteo.com/v1/forecast?${params}`;
const res = await fetch(url);
if (!res.ok) throw new Error(`Weather API error: ${res.status}`);
return res.json() as any;
The geocoding URL hard-codes language=en, which forces English localization regardless of the user's preferences or locale. This is a natural-language policy concern because the skill does not offer a language choice or document a justified locale restriction.
Detected: suspicious.dangerous_exec