news-sentiment
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implementation follows standard practices for fetching and displaying external data. It uses a localized Python script to interface with a reputable data provider and outputs structured JSON.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves headlines and article content from external news sources. While this exposes the agent to untrusted text, the risk is negligible as the skill lacks capabilities that could be exploited by such text (e.g., it does not perform file writes, shell execution, or network exfiltration based on the news content).
- Ingestion points: News data retrieved via the
yfinancelibrary inscripts/news.py. - Boundary markers: None specified; data is intended for presentation to the user.
- Capability inventory: The script's logic is restricted to formatting and printing data; no system-modifying capabilities are present.
- Sanitization: None; the raw article text is processed as standard output strings.
Audit Metadata