The Agent Skills Directory

[SAFE]: The skill provides standard statistical analysis code using well-known libraries such as numpy, statsmodels, and scikit-learn. No malicious patterns, data exfiltration, or unauthorized command executions were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes time-series data in functions like test_stationarity and analyze_stationarity.
Ingestion points: Data is passed via the series argument in test_stationarity and feature_series in analyze_stationarity within SKILL.md.
Boundary markers: None present.
Capability inventory: The skill is limited to statistical calculations and printing results; it lacks file system write access, network capabilities, or subprocess execution across its scripts.
Sanitization: None present, but the statistical functions in statsmodels do not execute instructions embedded in data.

ml4t-stationarity-tests