Skills
Navigate
skills/sandbaseai/sandbase-skills/google-news-research/Gen Agent Trust Hub

google-news-research

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes news articles from external sources, which creates a potential surface for indirect prompt injection where instructions could be hidden in article text.
  • Ingestion points: Articles are fetched using the google_news_bulk_articles tool as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands within the retrieved news content.
  • Capability inventory: The skill uses platform-specific tools sandbase_call_tool and sandbase_describe_tool to interact with external APIs.
  • Sanitization: No explicit sanitization or filtering of external news content is specified before the agent processes and summarizes the information.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 11:45 AM