news
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses specific, well-known news URLs to provide information to the user. No suspicious patterns such as credential theft, hidden code, or unauthorized commands were found.
- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes external web content. Ingestion points: Public news URLs listed in SKILL.md. Boundary markers: None. Capability inventory: Uses the
browser_usetool for web access. Sanitization: Not present. This risk is expected for a news aggregation tool and is managed by the model's safety filters.
Audit Metadata