google-news
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill enables an agent to ingest untrusted data from news.google.com, which is a surface for indirect prompt injection attacks. \n
- Ingestion points: Google News RSS feeds. \n
- Boundary markers: None present in documentation. \n
- Capability inventory: Documented ability to fetch and parse headlines. \n
- Sanitization: No evidence of content sanitization or filtering. \n- Data Exposure & Exfiltration (SAFE): No credentials or sensitive files are accessed; data fetching is restricted to public URLs. \n- External Downloads (SAFE): The skill references standard public news feeds and reputable libraries.
Audit Metadata