value-dividend-screener
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on the 'requests' library, which is a standard and highly trusted package for HTTP communication in the Python ecosystem.
- [COMMAND_EXECUTION]: The skill instructions involve running a local script ('scripts/screen_dividend_stocks.py') that performs data retrieval and analysis tasks.
- [DATA_EXFILTRATION]: The skill performs network requests to the official domains of well-known financial services, including financialmodelingprep.com and finviz.com. These operations transmit user-provided API keys as required for the skill's documented functionality and target established service endpoints.
- [PROMPT_INJECTION]: The skill ingests data from external financial APIs, representing a surface for indirect prompt injection. The risk is assessed as safe because the data is primarily quantitative and is parsed using structured formats (JSON and CSV) through standard libraries. Mandatory Evidence Chain: 1. Ingestion points: FMP and FINVIZ API responses in 'scripts/screen_dividend_stocks.py'. 2. Boundary markers: Structured parsing of JSON/CSV data. 3. Capability inventory: Local file writing and network operations (requests.get). 4. Sanitization: Use of standard Python 'json' and 'csv' parsers.
Audit Metadata