weather
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches weather information from several external domains: 中华万年历 (wthrcdn.etouch.cn), sojson (t.weather.sojson.com), and wttr.in. These are established public services used as intended for weather forecasting.
- [SAFE]: The Python script in
scripts/main.pyexplicitly disables SSL hostname checking and certificate verification (ssl.CERT_NONE). While this is a security best-practice violation that could expose connections to interception, it is common in simple scripts and does not indicate malicious intent in this context. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes and displays data from external web sources.
- Ingestion points: Weather API responses from external domains processed in
scripts/main.py. - Boundary markers: Absent. Data from the APIs is returned directly to the agent without delimiters.
- Capability inventory: Network read operations using
urllib.requestinscripts/main.py. - Sanitization: Data is parsed as JSON, but the extracted text fields (e.g., weather tips and descriptions) are not sanitized or escaped before being provided to the agent.
Audit Metadata