fundamentals
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts to retrieve and calculate financial metrics. This is the intended behavior for providing data to the agent.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the 'yfinance' library to fetch data from Yahoo Finance. This is a standard industry-recognized library for accessing public market data.
- [PROMPT_INJECTION]: The skill fetches data from an external source (Yahoo Finance) to present to the agent, creating a surface for indirect prompt injection.
- Ingestion points: Financial data retrieved via the 'yfinance' library.
- Boundary markers: None present.
- Capability inventory: Local script execution via 'uv run python'.
- Sanitization: Input symbols are normalized to uppercase.
Audit Metadata