dividend-growth-pullback-screener

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches financial data from well-established services, including Financial Modeling Prep (financialmodelingprep.com) and FINVIZ Elite (elite.finviz.com). These downloads are restricted to structured financial data (JSON/CSV) used for analysis.
  • [COMMAND_EXECUTION]: The skill includes a Python script (screen_dividend_growth_rsi.py) that performs data processing, calculation of technical indicators, and file writing to generate reports. The execution is localized to the stated screening purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external APIs which could potentially contain malicious content aimed at the agent.
  • Ingestion points: Data enters through FINVIZClient.screen_stocks and FMPClient._get in screen_dividend_growth_rsi.py.
  • Boundary markers: The generated Markdown report does not include specific boundary delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill performs network requests and writes JSON/Markdown files to the local filesystem.
  • Sanitization: The script performs data validation (e.g., checking for valid numbers and dates) but does not sanitize text fields (e.g., company names) before including them in reports.
  • [CREDENTIALS_UNSAFE]: The skill manages API keys using environment variables or command-line arguments, following standard security practices for CLI utilities. No hardcoded credentials or unsafe storage patterns were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:05 AM
Security Audit — agent-trust-hub — dividend-growth-pullback-screener