skills/hkuds/vibe-trading/yfinance/Gen Agent Trust Hub

yfinance

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a read-only interface to Yahoo Finance. It describes data fetching operations for OHLCV bars, financial statements, and institutional holdings without requesting sensitive permissions or accessing private local data.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with official Yahoo Finance endpoints (query1.finance.yahoo.com and query2.finance.yahoo.com) to retrieve market data. These are well-known, unauthenticated public services used for financial research.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web sources, creating a potential surface for indirect prompt injection. However, the risk is assessed as low because the data is structured (JSON/CSV) and primarily consists of numeric financial values (prices, ratios, volumes).
  • Ingestion points: Market data is fetched from Yahoo Finance API endpoints via the requests library.
  • Boundary markers: The skill returns data as structured Python dictionaries or JSON strings, maintaining clear boundaries between data and instructions.
  • Capability inventory: The skill is restricted to data retrieval; it does not contain capabilities for file system modification or arbitrary shell command execution based on the fetched data.
  • Sanitization: The documentation specifies that internal loaders normalize symbols and remove malformed rows before returning data to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 05:36 PM