risk-and-portfolio
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference and implementation guide for financial risk management. It provides valid Python implementations for calculating Sharpe ratios, Kelly criterion, and Monte Carlo simulations using standard libraries like numpy and pandas.
- [DATA_EXPOSURE]: The skill includes a Multi-Account Manager that stores trading data (balances, P&L, account identifiers) in a local JSON file within the agent's environment. This is a functional requirement for the skill's purpose and does not involve exfiltration to external systems.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process external data sources such as trade journals and account summaries.
- Ingestion points: Local storage files and user-provided DataFrames processed by analytical functions.
- Boundary markers: Not applicable, as the data is used for quantitative calculation rather than natural language generation.
- Capability inventory: File system operations for creating data directories and saving JSON/PNG reports.
- Sanitization: Standard data handling through established Python libraries.
Audit Metadata