NYC

generating-trading-signals

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted external data retrieved from financial markets.
  • Ingestion points: Market data fetched via the yfinance library is passed to scripts/scanner.py.
  • Boundary markers: The skill documentation does not specify explicit delimiters or 'ignore' instructions for the data being processed.
  • Capability inventory: The skill utilizes Bash(python:*) to execute local analysis scripts.
  • Sanitization: While scripts are not provided, the use of pandas and numpy typically involves structured numerical data, reducing the likelihood of successful injection compared to free-text processing.
  • [External Downloads] (LOW): The skill instructions include the installation of several Python packages (yfinance, pandas, numpy, matplotlib). These are standard, widely-used libraries for data science and finance and are considered acceptable dependencies.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:36 AM