backtrader

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the backtrader and matplotlib packages via pip, which are standard and well-known libraries in the Python ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external CSV files and Pandas DataFrames, which presents an attack surface for indirect prompt injection.
  • Ingestion points: The skill uses bt.feeds.YahooFinanceCSVData, bt.feeds.PandasData, and bt.feeds.GenericCSVData in SKILL.md to read data from external files such as stock_data.csv.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat external data as untrusted.
  • Capability inventory: The skill's functionality is limited to financial calculations, backtesting execution, and visualization using matplotlib. It does not include tools for network exfiltration or system modification.
  • Sanitization: The skill relies on the standard parsing mechanisms of the backtrader and pandas libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 03:36 PM