theme-detector

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves financial market data from several external services to perform its analysis.
  • Fetches industry and stock performance metrics from Finviz via both its public site and Elite API.
  • Accesses valuation data and ETF holdings through the Financial Modeling Prep (FMP) API.
  • Downloads historical market metrics using the yfinance library.
  • Retrieves technical indicator datasets from a specific public repository on GitHub (tradermonty/uptrend-dashboard).
  • [PROMPT_INJECTION]: The skill processes external market data that could potentially contain indirect prompt injection vectors.
  • Ingestion points: External CSV data and API responses are processed in scripts/uptrend_client.py, scripts/etf_scanner.py, and scripts/representative_stock_selector.py.
  • Boundary markers: The skill does not explicitly use delimiters or instructions to the model to ignore commands that might be embedded within descriptive data fields.
  • Capability inventory: The skill executes Python logic to aggregate data and generates Markdown reports in scripts/report_generator.py for the AI to interpret.
  • Sanitization: The skill employs robust numeric parsing for quantitative data (e.g., in _safe_float and _parse_market_cap), but descriptive string fields (like industry names) are passed directly into the final report without specific sanitization for instruction markers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:10 AM