value-dividend-screener

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's core logic is contained in the screen_dividend_stocks.py script, which performs data retrieval and fundamental analysis. It communicates exclusively with well-known and expected financial data providers (financialmodelingprep.com and finviz.com).
  • [SAFE]: The skill follows security best practices for secret management. It instructs the user to provide API keys through environment variables and includes specific logic in fmp_client.py and screen_dividend_stocks.py to redact these keys from any standard error output or request exception messages, preventing accidental credential leakage in logs.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external financial APIs (FMP and FINVIZ) and interpolates it into a Markdown report template. Ingestion occurs in the screen_stocks and get_income_statement methods. However, the skill lacks exploitable capabilities (no eval(), exec(), or arbitrary shell execution) and performs validation on numeric data using the _price_bars.py utility. The risk of the AI agent being manipulated by malicious API responses is mitigated by the skill's narrow scope and lack of dangerous tools.
  • [EXTERNAL_DOWNLOADS]: Network requests are restricted to the official endpoints of the financial data providers required for the skill's stated purpose. These requests are made using the standard requests library and do not involve the execution of remote code.
  • [COMMAND_EXECUTION]: The skill executes local Python code to perform financial calculations. It does not spawn subprocesses with user-controlled input or perform any dangerous system-level commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 04:51 PM