The Agent Skills Directory

[SAFE]: The skill performs its stated function of financial analysis without any detected security risks. The scripts and instructions are well-documented and follow standard practices for data analysis and visualization.
[EXTERNAL_DOWNLOADS]: The skill fetches financial time-series data from legitimate and well-known services: Yahoo Finance (via the yfinance library), Stooq (via direct CSV download in scripts/generate_chart.py), and the Federal Reserve Economic Data (FRED) service (via pandas-datareader). These downloads are essential for the skill's purpose and target established, trusted financial data providers.
[COMMAND_EXECUTION]: Command execution is limited to installing required Python dependencies and running the analysis scripts provided with the skill. There are no patterns of arbitrary or dangerous shell command execution.
[DATA_EXFILTRATION]: No sensitive data access or exfiltration mechanisms were found. The skill operates on public financial data and generates local output files (JSON, Markdown, and PNG charts) for the user's review.
[PROMPT_INJECTION]: The instructions in SKILL.md and the workflows follow a clear, professional structure. No prompt injection attempts, safety filter bypasses, or instruction-override patterns were identified.

evaluate-exponential-trend-deviation-regimes