backtesting-trading-strategies

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches historical trading data from reputable and well-known financial services, including Yahoo Finance, CoinGecko, and Tushare.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes market data from external APIs, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: External market data is retrieved by fetch_data.py and read by backtest.py from local CSV caches.
  • Boundary markers: The skill does not employ specific delimiters or instruction-ignore markers when processing the ingested price data.
  • Capability inventory: The skill is capable of writing trade logs, equity curves, and visual charts to the local file system using the processed data.
  • Sanitization: Market data is parsed into structured pandas DataFrames, which effectively constrains the external content to numerical price and volume information.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:54 PM